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 9 of 21

401. CVPR 2026Spatia Video Generation with Updatable Spatial Memory
402. CVPR 2026Spatial Matters Position-Guided 3D Referring Expression Segmentation
403. CVPR 2026Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
404. CVPR 2026Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesis
405. CVPR 2026SpeeDe3DGS Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and
406. CVPR 2026Speeding Up the Learning of 3D Gaussians with Much Shorter
407. CVPR 2026Splatent Splatting Diffusion Latents for Novel View Synthesis
408. CVPR 2026SplatSuRe Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting
409. CVPR 2026SR3R Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting
410. CVPR 2026ST4R-Splat Spatio-Temporal Referring Segmentation in 4D Gaussian Splatting
411. CVPR 2026STAC Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
412. CVPR 2026STAvatar Soft Binding and Temporal Density Control for Monocular 3D
413. CVPR 2026Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting
414. CVPR 2026Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generation
415. CVPR 2026SunFaded Illumination-Aware Gaussian Splatting for Dark Scenes with Camera-Mounted Active
416. CVPR 2026SuP Sub-cloud Driven Point Cloud Registration
417. CVPR 2026Superman Unifying Skeleton and Vision for Human Motion Perception and
418. CVPR 2026SV-GS Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting
419. CVPR 2026TACO Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D
420. CVPR 2026TagSplat Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
421. CVPR 2026TAlignDiff Automatic Tooth Alignment assisted by Diffusion-based Transformation Learning
422. CVPR 2026TALO Pushing 3D Vision Foundation Models Towards Globally Consistent Online
423. CVPR 2026TeHOR Text-Guided 3D Human and Object Reconstruction with Textures
424. CVPR 2026Text-guided Feature Disentanglement for Cross-modal Gait Recognition
425. CVPR 2026TGSFormer Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
426. CVPR 2026The LLM Bottleneck Why Open-Source Vision LLMs Struggle with Hierarchical
427. CVPR 2026Thermal is Always Wild Characterizing and Addressing Challenges in Thermal-Only
428. CVPR 2026ThinkingViT Matryoshka Thinking Vision Transformer for Elastic Inference
429. CVPR 2026TokenGS Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
430. CVPR 2026TokenSplat Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
431. CVPR 2026Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondence
432. CVPR 2026TopoMA Topology-Guided Multi-Agent Dense RGB 3D Reconstruction via Distributed Inference
433. CVPR 2026TopoMesh High-Fidelity Mesh Autoencoding via Topological Unification
434. CVPR 2026TouchDream 3D Object Completion through Imagined Touch
435. CVPR 2026Towards Foundation Models for 3D Scene Understanding Instance-Aware Self-Supervised Learning
436. CVPR 2026Towards Knowledge-augmented Bayesian Deep Learning For Computer Vision
437. CVPR 2026Towards Robust Vision Transformers Path Dependency Analysis and a Simple
438. CVPR 2026Tracking by Predicting 3-D Gaussians Over Time
439. CVPR 2026Tracking-Guided 4D Generation Foundation-Tracker Motion Priors for 3D Model Animation
440. CVPR 2026tttLRM Test-Time Training for Long Context and Autoregressive 3D Reconstruction
441. CVPR 2026Turbo-GS Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
442. CVPR 2026TWINGS Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
443. CVPR 2026UAVLight A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial
444. CVPR 2026ULF-Loc Unbiased Landmark Feature for Robust Visual Localization with 3D
445. CVPR 2026Unblur-SLAM Dense Neural SLAM for Blurry Inputs
446. CVPR 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
447. CVPR 2026Uni3R Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian
448. CVPR 2026UniCorrn Unified Correspondence Transformer Across 2D and 3D
449. CVPR 2026UniSH Unifying Scene and Human Reconstruction in a Feed-Forward Pass
450. CVPR 2026Unlocking the Power of Critical Factors for 3D Visual Geometry

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.