๐ง Depth, Normals & Stereo¶
๐ท CVPR2026 ยท 43 paper notes
๐ Same area in other venues: ๐ง NeurIPS2026 (3) ยท ๐๏ธ ECCV2026 (39) ยท ๐ฌ ICLR2026 (10) ยท ๐ค AAAI2026 (4) ยท ๐ง NeurIPS2025 (5) ยท ๐น ICCV2025 (15)
๐ฅ Top topics: Depth Estimation ร18 ยท Few-/Zero-Shot Learning ร7 ยท Stereo Matching ร6 ยท Diffusion Models ร3
- 240FPS Stereo Vision from Monocular Mixed Spikes
-
A single monocular spike camera is used to optically mix left and right views onto the same sensor, with one view subjected to periodic 60 Hz modulation. Through a two-stage processโ"Least Squares Baseline Decoupling + SMS-Net Depth Refinement"โa 240 FPS binocular video is reconstructed from the mixed spike stream. This approach maintains the compact hardware and data efficiency of a monocular setup while achieving depth estimation accuracy close to the "theoretical upper bound."
- AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimation
-
AIMDepth introduces Mamba (State Space Models) to image-event monocular depth estimation for the first time. It employs a two-level modal alignment before fusion: bidirectional prior injection in the frequency domain (SCPG) for input-level alignment, and an asymmetric feature selection encoder (AME) for feature-level alignment. These are combined with a modal interaction local refinement module (ModiLocal), achieving SOTA performance on MVSEC/DENSE with only 8.69 GFLOPs.
- Any Resolution Any Geometry: From Multi-View To Multi-Patch
-
A single ultra-high-definition image is decomposed into patches and treated as "virtual multi-views" within a VGGT-style framework for joint processing. Combined with cross-patch attention for global consistency reasoning, the model outputs sharp and globally coherent high-resolution depth maps and surface normals in a single forward pass, reducing AbsRel on UnrealStereo4K from 0.0582 to 0.0291.
- Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
-
A new paradigm called "Artistic Disparity Synthesis" (Art3D) is proposed, shifting the goal of 2D-to-3D conversion from geometric accuracy to artistic expression. Through a dual-path architecture that decouples global depth style and local artistic effects, the model learns directorial intent from professional 3D movie data.
- Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
-
Addressing asymmetric stereo matching where "one eye is an event camera and the other is a standard RGB camera," this paper proposes Bi-CMPStereo. It utilizes a cross-domain adapter and self-reconstruction constraints to align both modalities into a "canonical space of a single target domain." By alternating between event and image as the target domain in a bidirectional fashion and fusing the results, the method significantly outperforms previous SOTA models (e.g., ZEST) in accuracy and generalization on DSEC, MVSEC, and M3ED datasets.
- Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
-
Addressing the "extremely sparse + low resolution + noisy" depth maps from direct Time-of-Flight (dToF) sensors, this paper proposes a depth-guided dual-branch ViT encoder with masked joint attention. This allows sparse depth to unidirectionally guide RGB features without being contaminated by RGB cues, coupled with a lightweight DPT decoder to directly output dense metric depth. Trained entirely on a simulation pipeline covering flash/rotating dToF synthetic data, the model achieves zero-shot generalization across 6 datasets and 3 real dToF devices, matching or exceeding Prev. SOTA while being 20ร faster and using 10ร less VRAM.
- Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
-
This paper proposes DAP (Depth Any Panoramas), a foundation model for panoramic metric depth estimation. Utilizing a "data-in-the-loop" approach, it feeds 2M indoor/outdoor and synthetic/real panoramic images into a three-stage pseudo-label distillation pipeline. Combined with a DINOv3 backbone, a plug-and-play distance mask head, and a set of distortion-aware geometric/sharpness losses, DAP achieves zero-shot SOTA on multiple benchmarks including Stanford2D3D, Matterport3D, and Deep360, providing particularly stable absolute scale predictions for outdoor long-range and sky regions.
- Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation
-
HypoDepth reformulates event-image monocular depth estimation from "direct regression of continuous depth" to "constrained search within discrete depth hypotheses." By utilizing a lightweight 3D cost volume and a GRU iterative unit, it progressively refines residual depth from low to high resolution. It achieves SOTA on DSEC and MVSEC, with a Tiny version capable of real-time operation on resource-constrained devices.
- DepthFocus: Controllable Depth Estimation for See-Through Scenes
-
DepthFocus redefines stereo depth estimation from a "passive output of the nearest surface" to a "controllable process driven by a physical reference distance \(c\)." Using a steerable ViT that dynamically modulates features through two modulesโConditional MoE and Direct Condition Injectionโthe network "peels away" transparent or reflective occlusions layer-by-layer like human eye focusing, achieving SOTA on both standard single-layer benchmarks and complex multi-layer scenes.
- Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectance
-
Using a unified "spatial-angular 4D structured light" hardware (LED array + LCD mask + single camera), this work differentiably optimizes the next set of light/mask patterns in real-time during the capture process to minimize pixel-wise depth uncertainty. This enables efficient joint reconstruction of object shape (depth map) and reflectance (GGX SVBRDF) from a single viewpoint, reducing exposure time by up to 100\(\times\) and total acquisition time by 2\(\times\).
- Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
-
The authors discover that "Image-scale Editing (I2I) diffusion models" are inherently deterministic image-to-image mappings, making them better suited for dense perception than the commonly used "Text-to-Image (T2I)" models. They perform full-parameter fine-tuning on the FLUX.1 Kontext editor to create a unified depth/normal/matting perceiver. By incorporating a pixel-space consistency loss and a theoretically optimal square-root depth mapping, the model achieves SOTA results across three tasks with single-step inference using only ~74,000 training images.
- EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
-
This paper proposes EventHub, a data factory for event-based stereo matching training without LiDAR or other active sensor annotations. By generating proxy events and depth labels via novel view synthesis and transferring knowledge from RGB stereo models through cross-modal distillation, the trained event stereo models surpass LiDAR-supervised models in cross-domain generalization (reducing error by up to 50% on M3ED and MVSEC).
- Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
-
FoundationStereo, which features strong zero-shot performance but slow execution, is compressed using a "divide and conquer" strategy comprising three pillars: feature distillation, block-wise search for cost filtering, and pruning of the refinement module. Supplemented by an automated pseudo-labeling pipeline processing 1.4M real stereo pairs, this approach maintains near-original zero-shot accuracy at real-time frame rates, achieving a speedup of over 10x compared to FoundationStereo.
- FE2E: From Editor to Dense Geometry Estimator
-
This paper systematically analyzes the differences in fine-tuning behavior between image editing models and generative models for dense geometry estimation tasks. It discovers that editing models possess a natural structural prior advantage. Based on this, the FE2E framework is proposed, which for the first time adapts a DiT-based image editing model into a joint depth and normal estimator, significantly outperforming existing SOTA in zero-shot scenarios (reducing AbsRel by 35% on ETH3D).
- GS-ASM: 2DGS-Supervised Active Stereo Matching
-
Addressing the accuracy limitations in active stereo matching caused by the lack of ground truth (GT) and reliance on self-supervision, this paper utilizes 2D Gaussian Splatting (2DGS) to reconstruct geometry from real scenes and render high-quality disparity "proxy labels." This transforms unsupervised active stereo networks into "supervised" training, complemented by a hybrid supervision regularization strategy that dynamically balances proxy supervision and self-supervision. The method achieves SOTA performance across multiple backbones, surpassing commercial RealSense D435 depth cameras.
- Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
-
HairGuard leverages image matting datasets to construct fine-grained depth supervision for soft boundaries (e.g., hair). It employs a "depth fixer + scene painter + color fuser" trio as a plug-and-play solution to correct depth, repair occlusions, and fuse textures, achieving SOTA performance on soft boundary details in monocular depth, stereo conversion, and novel view synthesis.
- InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
-
InfiniDepth reformulates depth from "pixel-wise values on a discrete grid" to a "neural implicit field from continuous 2D coordinates to depth." Using a multi-scale local implicit decoder, it queries depth at any \((x,y)\) coordinate, thereby bypassing training resolution limits to directly predict razor-sharp depth maps at arbitrary resolutions. It also introduces a query strategy that allocates sampling budgets based on surface area to improve novel view synthesis (NVS) under large viewpoints.
- Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
-
Iris proposes a deterministic diffusion framework that injects real-world priors into diffusion models through a two-stage "Prior-to-Geometric" (PGD) schedule. The first stage utilizes Spectral Gated Distillation (SGD) at high timesteps to extract low-frequency layout priors from a teacher model. The second stage refines high-frequency geometric details using synthetic data at low timesteps, while introducing Spectral Gated Consistency (SGC) for cross-stage high-frequency alignment. It achieves SOTA zero-shot depth estimation performance under limited data and computational budgets.
- Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
-
Iris systematically validates a naive hypothesis: feeding additional text descriptions of scene objects into a diffusion-based monocular depth estimator leverages the "text \(\leftrightarrow\) 3D scene" conditional distribution learned during text-to-image pre-training. This reduces the depth solution space, leading to overall zero-shot accuracy improvements across three diffusion MDEs (Marigold, Lotus, and E2E-FT), particularly for small objects and blurry regions, while also accelerating training and inference convergence.
- Lite Any Stereo: Efficient Zero-Shot Stereo Matching
-
Lite Any Stereo is proposed, which utilizes a hybrid 2D-3D cost aggregation module and a three-stage million-scale data training strategy (supervised โ self-distillation โ real-world knowledge distillation). With less than 1% of the computation (33G MACs) compared to SOTA precise methods, it ranks 1st on four real-world benchmarks, demonstrating for the first time that ultra-lightweight models can possess strong zero-shot generalization capabilities.
- LiteSense: Lifting Lightweight ToF with RGB for High-Resolution Metric Depth Estimation
-
LiteSense fuses Compact Normalized Histograms (CNH) from multi-zone ToF sensors with RGB images using patch-wise cross-attention within a U-Net. With only 5.5M parameters, it approaches the performance of SOTA large models in indoor metric depth estimation and significantly outperforms the comparable RGB-ToF method DELTAR.
- MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation
-
Addressing the "unrecoverable scale in monocular metric depth when camera intrinsics are unavailable during both training and inference," this paper observes that while RGB remains nearly invariant when focal length and scene depth change couplingly, the spectral statistics of edges shift systematically. The authors propose the Spectral Quantile Estimator (SQE) to extract a scalar score as a scale proxy from the Fourier spectrum of predicted edge maps to calibrate depth. MD2E achieves SOTA in Monocular Metric Depth Estimation (MMDE) across 6 unseen benchmarks under zero-shot and fine-tuning settings (e.g., A.Rel decreased by 53.0% and RMS by 41.9% on iBIMS-1).
- PIP-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching
-
Reveals spatial sparsity and temporal redundancy in iterative stereo matching disparity updates. Proposes Progressive Iterations Pruner (PIP) to compress 32 iterations into 1, a collaborative learning paradigm for depth prior transfer without independent monocular encoders, and a hardware-aware FlashGRU operator (7.28ร speedup). This enables high-precision iterative stereo matching to achieve real-time inference on Jetson Orin NX (75ms/frame, 320ร640) for the first time.
- PromptDepth: Efficient and Promptable Geometric 3D Vision Model for Embodied Intelligence
-
PromptDepth unifies "panoptic depth, instance depth, tracking depth, and stereo depth" into a single promptable dense prediction task. A feed-forward network learns geometric representations, switching outputs via different task tokens/points/mask prompts. Combined with ILDS loss and Gram Anchoring to resolve training conflicts between panoptic and instance depth, the model achieves SOTA on multiple benchmarks using only synthetic data. It doubles inference speed and is designed for real-time 3D understanding in embodied agents.
- PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
-
This paper proposes the Prompt Recurrent Unit (PRU), which utilizes the DPT decoder of monocular depth foundation models as an iterative refinement module (replacing GRU). By injecting monocular structural cues and stereo motion cues through Structure and Motion Prompts via residual addition, it achieves state-of-the-art (SOTA) zero-shot stereo matching performance without destroying monocular priors, reducing error by nearly 50% on Middlebury 2021.
- Radar-Guided Polynomial Fitting for Metric Depth Estimation
-
POLAR reformulates the task of "transforming scale-invariant monocular depth estimation (MDE) into metric depth using sparse radar points" as a polynomial fitting problem. It utilizes radar features to predict a set of polynomial coefficients to apply non-uniform, depth-dependent corrections to MDE depth (instead of traditional global scale-and-shift affine transforms). This approach reduces MAE/RMSE by 24.9%/33.2% on average across three datasets while achieving real-time performance (40 fps) with minimal computational overhead.
- Revisiting Optimal Coding for I-ToF under Practical Sensor Constraints
-
This paper derives the depth error of I-ToF cameras under a realistic noise model into a computable "depth variance metric." It directly integrates hardware constraintsโsuch as peak power, bandwidth, binary waveforms, and mutually exclusive multi-tapsโinto the design phase. This allows for searching the optimal coding schemes within a constrained feasible space. The two discovered schemes (for high/low SNR) consistently outperform Hamiltonian and double ramp codes in both simulations and on commercial sensors.
- RoSAMDepth: Robust Self-supervised Depth Estimation Leveraging Segment Anything Model
-
RoSAMDepth utilizes object-level masks generated offline by SAM as priors, injecting them into a self-supervised monocular depth framework from three perspectives: "representation space contrast," "region-level outlier suppression + Gaussian likelihood smoothing," and "object-level reliability weighting." This allows the model to predict depth with sharper boundaries and better intra-object consistency under adverse conditions such as night and rain.
- SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation
-
SCE-Depth proposes a hardware-software co-designed framework consisting of a "biomimetic spherical compound eye camera + spherical neural network." It processes compound eye images natively on the HEALPix spherical grid to avoid planarization distortions and utilizes the "distance-decaying depth-sensitive gradients" naturally generated by overlapping fields of view of adjacent ommatidia. Combined with a Spherical Gradient Feature Extractor (SGFE) and Spherical Gradient Loss (SGL), it significantly reduces wide-FOV depth errors, especially in peripheral regions.
- SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping
-
SeeGroup models multi-layer depths of transparent objects as an "intensity function" along the depth axis. By utilizing a recursive decomposition module, the model adaptively decides how to group depth layers, combined with a permutation-invariant likelihood loss. It improves quaternary relative depth accuracy from 61.34% to 70.09% on the LayeredDepth real-world benchmark.
- Seeing Depth Through Frequency and Motion: A Progressive Training Paradigm for Monocular Depth Estimation
-
Addressing the issues where blurred boundaries stem from downsampling frequency aliasing and PoseNets lack sufficient cross-frame motion modeling, this paper proposes the plug-and-play Frequency-Guided Sampling (FGS) module to preserve high-frequency details and the PoseQuery Network (PQNet) using channel-aligned attention for cross-frame motion modeling. Combined with a progressive three-stage decoupled training paradigm to maximize the complementarity between depth and pose, the method achieves a 4.1% reduction in Sq Rel compared to a strong baseline on KITTI.
- SO(3)-Equivariant ViT-Adapter for Data-Efficient Zero-Shot Sim-to-Real Indoor Panoramic Depth Estimation
-
Add an SO(3)-equivariant adapter to a frozen perspective pre-trained ViT (Depth Anything V2). By training on only 6.5K synthetic panoramas with zero real data, the framework transfers the zero-shot generalization capabilities of perspective models to 360ยฐ panoramas, outperforming real-data-dependent PanDA in zero-shot sim-to-real on Matterport3D / Stanford2D3D.
- SPE-MVS: Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth Priors
-
SPE-MVS utilizes metric monocular depth priors to construct a "Spatial Position Encoding (SPE)" in a unified coordinate system for each pixel across views. This encoding is fed into feature extraction and cost volume construction alongside the images. A monocular depth-guided two-stage refinement module is then used to polish the probability maps, significantly improving MVS reconstruction quality in areas where photometric matching fails, such as weak-textured and non-Lambertian surfaces.
- SpiderCam: Low-Power Snapshot Depth from Differential Defocus
-
SpiderCam utilizes a beam-splitting prism and two low-power image sensors to capture a pair of differential defocus images. It executes an optimized Differential Depth from Defocus (DfDD) algorithm in a streaming fashion on a low-power FPGAโone too small to store even a single pair of full frames. This represents the first passive 3D camera in literature with a total power consumption under 1 Watt (624 mW @ 32.5 FPS) and an operating range exceeding half a meter.
- Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
-
The authors discover that the root cause of temporal jitter in monocular geometry foundation models (such as MoGe) on video streams is not geometric error, but rather frame-by-frame "scale-shift" drift, which is directly determined by the fluctuations in the mean and variance of latent features. Consequently, they propose a lightweight recurrent module DyFN (Dynamic Feature Normalization) that accounts for only 2% of the parameters. Keeping the backbone frozen and tuning only this module, DyFN uses a ConvGRU to memorize and dynamically predict and replace feature statistics, achieving SOTA temporal stability across four benchmarks without sacrificing single-frame accuracy.
- The Midas Touch for Metric Depth
-
MTD (Midas Touch for Depth) employs a training-free, mathematically interpretable "coarse-to-fine" algorithm to convert relative depth from foundation models into metric depth using extremely sparse 3D seeds (e.g., LiDAR or stereo matching). It aligns local scales via segment-wise graph optimization and performs pixel-level detailing using "discontinuity-aware geodesic cost + dynamic programming." It outperforms SOTA methods like BP-Net, DMD3C, and Marigold-DC in zero-shot depth completion and estimation, with a backend latency of only 1.9 ms.
- TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrast
-
The TR2M framework is proposed to predict pixel-level scale/shift maps using image and text descriptions, converting highly generalizable but scale-less relative depth into metric depth. Achieving cross-domain zero-shot metric depth estimation is realized with only 19M trainable parameters and 102K training images.
- UniDAC: Universal Metric Depth Estimation for Any Camera
-
UniDAC decouples monocular metric depth into two components: relative depth and a spatially-varying scale map. Using a unified model trained exclusively on perspective views, it achieves zero-shot metric depth estimation on wide field-of-view cameras like fisheye and 360ยฐ. By leveraging a depth-guided scale upsampling module and RoPE-ฯ, a positional encoding adapted for Equirectangular Projection (ERP) geometry, it significantly outperforms previous SOTA in cross-camera generalization.
- Variational Graph-based Normal Integration
-
This paper reformulates the "normal map โ depth" integration problem as a unified optimization objective on a directed weighted graph. It explicitly models depth discontinuities using triplets combined with a two-component Gaussian Mixture Model (GMM), and employs variational inference to alternatingly solve for depth and graph weights. This approach not only outperforms the current SOTA (BiNI) on regular grids but also directly handles scattered oriented points, which grid-based methods fail to process.
- VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
-
VGGT-360 reformulates panoramic monocular depth estimation as a problem of "reconstructing a globally consistent 3D model using VGGT-like 3D foundation models from multiple views and then reprojecting it back to the panorama." Through three training-free plug-and-play modules (Uncertainty-Guided Adaptive Projection, Structural Saliency-Enhanced Attention, and Correlation-Weighted 3D Refinement), it unifies fragmented depth results from independent view inference into cross-view consistent results, surpassing both supervised and training-free SOTA methods on multiple indoor and outdoor datasets in a zero-shot manner.
- What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
-
This paper systematically ablates the design space of synthetic training data for stereo matching (including floating objects, backgrounds, materials, and baselines). It finds that the combination of "realistic indoor scenes + dense floating objects + wide baselines" is optimal. Based on these findings, WMGStereo-150k is constructed, which outperforms hybrid training using four classic datasets while using only a single dataset.
- XPaintNet: An eXtreme Lightweight Framework for Stereoscopic Conversion without Inpainting Network
-
To address the issues of slow performance and artifacts at occlusion boundaries in the traditional "depth estimation + forward warping + heavy inpainting network" pipeline for 2D-to-3D stereoscopic conversion, this paper proposes Bi-Warp (bidirectional warp fusion) to completely eliminate the inpainting network. Based on this, a lightweight network named XPaintNet is constructed, which achieves 100+ FPS at 2K resolution while matching SOTA quality.
- Zero-Shot Depth Completion with Vision-Language Model
-
Sparse depth is injected into a minimally modified VLM (Qwen2.5-VL 3B) via "visual tokens + text prompts + text supervision." This allows the model to understand "where to fill and where to preserve" like verbal instructions, enabling zero-shot depth completion without dense ground truth and achieving up to a 17.3% improvement across 7 cross-domain benchmarks.