📚 Pretraining

🎞️ ECCV2026 · 15 paper notes

📌 Same area in other venues: 📷 CVPR2026 (5) · 🔬 ICLR2026 (79) · 💬 ACL2026 (12) · 🧪 ICML2026 (27) · 🤖 AAAI2026 (9) · 🧠 NeurIPS2025 (51)

🔥 Top topics: Adversarial Robustness ×3 · Face & Gaze ×2

360Anything: Geometry-Free Lifting of Images and Videos to 360°

360Anything proposes a geometry-free diffusion Transformer framework that treats perspective inputs and panoramic targets uniformly as token sequences. By concatenating these sequences, the model autonomously learns the geometric correspondences between them without requiring any camera metadata. It lifts arbitrary-view images/videos into gravity-aligned, seamless 360° panoramas, completely outperforming prior state-of-the-art methods that rely on ground-truth camera parameters in both image and video tasks.

FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

FAIR incorporates texture-orthogonal Scene Composition Structure (SCS) as a privileged geometric prior during training to smooth decision boundaries and penalize texture-biased shortcut learning, subsequently discarding the prior at inference to achieve massive cross-generator generalization gains with zero computational overhead.

GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition

GryphOne redefines handwritten mathematical expression recognition (HMER) from autoregressive sequence generation to an iterative symbol refinement process via discrete masked diffusion. It maintains syntactic consistency under local editing using Symbol-Aware Tokenization (SAT) and enhances refinement stability through Random-Mask Mutual Learning (RMML). This approach comprehensively outperforms re-implemented autoregressive baselines and commercial HMER systems on MathWriting, achieving a 5.51% CER and a 59.9% ExpRate.

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Reveals that vision encoders encode imperceptible camera acquisition and image processing metadata traces because pretraining datasets introduce spurious metadata-semantics correlations exploited as shortcuts, and provides training augmentation and post-hoc adversarial mitigation strategies that generalize across unseen attributes.

Map2World: Segment Map Conditioned Text to 3D World Generation

To overcome data scarcity and narrow domain restrictions in 3D world synthesis, Map2World introduces an arbitrary-shaped segment map conditioned framework that scales pretrained TRELLIS asset priors into complete, layout-controllable, scale-consistent, and detailed large-scale 3DGS worlds using 3D MultiDiffusion, spectral initial noise optimization, and a latent detail enhancer.

PolyLayout: Multi-room Manhattan Layout Estimation

PolyLayout parameterizes multi-room indoor layouts as 3D Manhattan polygons with shared orientation and floor/ceiling heights, formulating a differentiable objective over DINOv2 feature, edge, and confidence maps solved via coarse-to-fine Levenberg-Marquardt optimization with dynamic wall splitting and simplification.

Reflecting Process Expertise in Procedural Material Generation

MaterialApprentice reformulates procedural material creation from static graph-space synthesis into retrieval-time process reasoning over expert tutorial demonstrations, synthesizing intermediate process traces that a compiler grounds into executable Blender shader graphs.

Robustness Emerges Early in Training Dynamics, but Is Not Preserved

This paper discovers that shallow layers spontaneously develop robust representations and flat loss landscapes in early training but lose them during standard convergence; to retain these priors without modifying architectures, it introduces two parameter-free trajectory interventions—Early-Phase Stabilization (EPS) and Asymmetric Weight Reversion (AWR).

SceneDiff: A Benchmark and Method for Multiview Object Change Detection

Addressing object change detection across non-overlapping camera trajectories, this paper introduces the SceneDiff Benchmark with 350 video pairs and dense instance annotations, alongside a training-free framework combining 3D geometry co-registration and region-level feature comparison.

SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

To break through the decade-long bottleneck of scarce, low-resolution training data in document restoration, SyntheticDoc introduces a massive dataset of 1,000,000 high-resolution synthetic samples generated via ArcSim physics simulation and Blender path tracing, equipped with pixel-perfect UV and shading annotations, enabling a simple lightweight baseline to achieve new state-of-the-art results on DocUNet.

Continuous Heart Rate Variability Estimation from Egocentric Systems for Skill Assessment

Addressing the challenge where heavy head motion in wearable egocentric systems masks millisecond-level heartbeat intervals and frame-differencing leads to cumulative drift, EgoHRV introduces a 3D CNN with low-high decomposition and cross-domain frequency alignment to continuously extract accurate HR and HRV from eye-tracking video, boosting downstream EgoExo4D proficiency estimation accuracy by 17.8%.

ID-PreFeR: ID-Preserving Face Restoration with Mixed Data Quality

Addressing the bottlenecks of heavy personalization burdens and severe degradation under mixed-quality references in personalized face restoration, ID-PreFeR introduces a regularization-free lightweight cross-attention LoRA injector, an identity-quality disentanglement strategy using MLLM quality tokens with Min-SNR-\(\gamma\) weighting, and an inference-time ID-preserving sampling scheme, achieving state-of-the-art identity fidelity and perceptual restoration even with only a single high-quality reference image.

Mask-guided Semantic Alignment: Robust Learning with Noisy Labels via Temporal Attention Stability

To tackle model overfitting on false features under severe label noise, this paper introduces a temporal attention stability metric based on Class Activation Map (CAM) dynamics, adaptive differential masking, and mask-guided feature alignment (MSA), achieving 95.1% on CIFAR-10 and 55.6% on CIFAR-100 under 90% symmetric noise.

Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation

To tackle the systemic breakdown of monocular RGB surface normal estimators on reflective, textureless, and dark surfaces, Poppy presents a training-free test-time guidance framework that keeps arbitrary pretrained backbones frozen and refines geometry via input image offsets, output normal offsets, and differentiable polarization rendering.

Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP

To alleviate the performance degradation of CLIP when category names are semantically ambiguous or technical, this paper introduces a training-free Class-Discriminative Patch Set (CDPS) mining method that selects local visual features exhibiting high intra-class consistency and low inter-class ambiguity, coupled with an adaptive hybrid classifier combining global image-text alignment and local patch-level similarity.