ICML 2026 accepted papers on 3D vision
113 of the 6,341 papers accepted at ICML 2026 (1.8%) are on 3D vision, compared with 1.2% at ICML 2025. They fall into 6 topics.
See ICML 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
3D generation · 49 papers
- LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning (1 citation)
- 3D-DLP: Self-supervised 3D Object-centric Scene Representation Learning
- 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere
- A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
- Beyond Pixel Histories: World Models with Persistent 3D State
- CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors
- CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detection
- Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction
- DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
- Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
- EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
- Fast-SAM3D: 3Dfy Anything in Images but Faster
and 37 more in the interactive map.
Gaussian splatting · 21 papers
- 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
- AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
- Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
- GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
- GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM Reasoning
- Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
- S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
- TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
- TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
- 3DGS$^2$-TR: A Scalable Second-Order Trust-Region Method for 3D Gaussian Splatting
- Continuous Viewpoint Adaptation for Single View 3D Object Reconstruction
- CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos
and 9 more in the interactive map.
Depth and stereo · 17 papers
- Boosting Monocular Metric Depth Estimation via Bokeh Rendering
- GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
- GHOST: Geometry-Guided Hallucination of Opaque Surface Textures
- Structure-Aware Consistency Priors for Shape from Polarization in Complex Media
- TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation
- VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
- Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
- Bridging RGB and RAW: Single-step Deterministic Flow with Homogeneous Representation Alignment
- Creat3r: Confidence Reaggregation for Exploration-aware Active 3D Reconstruction
- DuRP: Dual-Stage Physics-Embedded Learning for Joint Radiance and Polarization Restoration
- INFER: Learning Implicit Neural Frequency Response Fields for Confined Acoustic Environments
- Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Spectral Super-Resolution for Snapshot Compressive Imaging
and 5 more in the interactive map.
Face and shape · 16 papers
- Adaptive Volumetric Mechanical Property Fields Invariant to Resolution
- CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
- CRAG: Can 3D Generative Models Help 3D Assembly?
- From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
- Geometry-Aware Neural Optimizer for Shape Optimization and Inversion
- Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
- Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
- LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
- TextMesh4D: Zero-shot Text-to-4D Mesh Generation
- EquiCAD: A Geometric Equivariant Neural Network for 3D Shape Classification
- FastSESR: Fast Scene-level Explicit Surface Reconstruction
- Focusing: View-Consistent Sparse Voxels for Efficient 3D VAE Training
and 4 more in the interactive map.
Human pose estimation · 8 papers
- DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation
- Doppler Prompting for Stable mmWave-based Human Pose Estimation
- Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
- Generalizable and Actionable Parts Pose Estimation with Symmetry Annotation-Free Learning Strategy
- DGG-HMR: Multi-Person Human Mesh Recovery with Depth-Guided Geometric Anchoring
- Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation
- Interleaved Selective State Space Models for Efficient WiFi-Based 3D Multi-Person Pose Estimation
- StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation