3D Vision papers, 2023–2026

Key findings

• 3D Vision went from 563 papers in 2023 to 1,010 in 2026, roughly 1.8x in three years.
• CVPR publishes the most 3D Vision work: 1,641 papers from 2023 to 2026, 51% of the four-venue total.
• The fastest-growing overlap is with Gaussian Processes: papers tagged with both rose from 0 in 2023 to 158 in 2026.
• Among the 5 topics under Computer Vision, it ranks #2 by 2026 paper count; the fastest grower in the group, Video Understanding, is up 2.6x versus 1.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
• ICML 20263D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
• ICLR 2026$\pi^3$: Permutation-Equivariant Visual Geometry Learning
• CVPR 20262D-LFM Lifting Foundation Model without 3D Supervision
• NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
• ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
• ICLR 20253D StreetUnveiler with Semantic-aware 2DGS - a simple baseline
• CVPR 20253D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
• NeurIPS 20243D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
• ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
• ICLR 20243D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
• CVPR 2024DaReNeRF: Direction-aware Representation for Dynamic Scenes
• NeurIPS 2023[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
• ICML 2023Efficient Graph Field Integrators Meet Point Clouds
• ICLR 2023$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
• CVPR 20233D Cinemagraphy From a Single Image
• NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
• ICML 20263DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
• ICLR 20263DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
• CVPR 20263D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors

All 3D Vision papers

1,008 papers, page 19 of 21

901. NeurIPS 2026MCSplat: Multi-View Photometric and Geometric Consistent Feed-Forward Gaussian Splatting for Driving Scenes
902. NeurIPS 2026MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
903. NeurIPS 2026MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
904. NeurIPS 2026MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI
905. NeurIPS 2026MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
906. NeurIPS 2026MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
907. NeurIPS 2026MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks
908. NeurIPS 2026NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
909. NeurIPS 2026NeuralFieldManifold: Reconstruction of LFP manifold with Lag Embedding
910. NeurIPS 2026NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting
911. NeurIPS 2026OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
912. NeurIPS 2026ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning
913. NeurIPS 2026OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction
914. NeurIPS 2026One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
915. NeurIPS 2026OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models
916. NeurIPS 2026Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design
917. NeurIPS 2026Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
918. NeurIPS 2026Patch4Patch: Restoring Structural Connectivity in Patch-based Vision Encoders
919. NeurIPS 2026PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion
920. NeurIPS 2026PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction
921. NeurIPS 2026PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
922. NeurIPS 2026PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression
923. NeurIPS 2026PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
924. NeurIPS 2026Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
925. NeurIPS 2026Point Clustering Encoders
926. NeurIPS 2026Point-to-Manifold Geometry: Flexibly Overcoming the Curse of Dimensionality in Neural Computational Units
927. NeurIPS 2026Point4D: Long-range 4D Motion Reconstruction
928. NeurIPS 2026Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders
929. NeurIPS 2026PolySplat: Workload-Regime-Aware Rasterization for 3D Gaussian Splatting
930. NeurIPS 2026PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs
931. NeurIPS 2026Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
932. NeurIPS 2026PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar Geometry
933. NeurIPS 2026Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers
934. NeurIPS 2026PRISM: Spectral Pruning and Reconstruction for Parameter-Efficient Model Merging of MLLMs
935. NeurIPS 2026Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
936. NeurIPS 2026Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
937. NeurIPS 2026Pygmalion: Bridging Reconstruction and Generation in Sparse Voxel-based 3D Modeling
938. NeurIPS 2026RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark Subsets
939. NeurIPS 2026RayTun3R: Online Camera Adaptation in 3D Foundation Models
940. NeurIPS 2026Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
941. NeurIPS 2026Register Anything Model for Generalizable and Robust Point Cloud Registration
942. NeurIPS 2026Reinforcement Learning for View-Adaptive Distillation in 3D Gaussian Compression
943. NeurIPS 2026Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation
944. NeurIPS 2026RelationVGGT : Visual Geometry Transformers for 3D Spatial Relation Segmentation
945. NeurIPS 2026RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding
946. NeurIPS 2026ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
947. NeurIPS 2026Residual-Autoregressive Context for 3D Gaussian Splatting Compression
948. NeurIPS 2026Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
949. NeurIPS 2026Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
950. NeurIPS 2026RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video

FAQ

How many 3D Vision papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,226 in total: 563 in 2023, 751 in 2024, 902 in 2025, 1,010 in 2026.

How many 3D Vision papers are at NeurIPS 2026?

NeurIPS 2026 has 211 3D Vision papers, versus 254 the year before.

How many 3D Vision papers are at ICLR 2026?

ICLR 2026 has 197 3D Vision papers, versus 162 the year before.

How many 3D Vision papers are at ICML 2026?

ICML 2026 has 117 3D Vision papers, versus 52 the year before.

How many 3D Vision papers are at CVPR 2026?

CVPR 2026 has 485 3D Vision papers, versus 434 the year before.

Which conference publishes the most 3D Vision papers?

CVPR, with 1,641 papers from 2023 to 2026.