Poster Session

E2E3D Workshop @ CVPR 2026, Denver, CO

June 3, 2026 · 5:05–6:00 PM · Exhibit Hall A

← Back to Workshop

Poster Board Assignment

All posters are presented in Exhibit Hall A on June 3, 2026, 5:05–6:00 PM. Please find your assigned board number below.

A Best Demo will be featured at the end of the session.

Board Side Title
249AMoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
249BSky2Ground: A Benchmark for Site Modeling under Varying Altitude
250ALoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
250BGeneralizable Sparse-View 3D Reconstruction from Unconstrained Images
251ANot All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis
251BWildDet3D: Scaling Promptable 3D Detection in the Wild
252AVideo2Assets: Extracting 3D Object Assets from Unconstrained Video
252BPAGE-4D: VGGT-4D Perception Via Disentangled Pose and Geometry Estimation
253APointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation ⭐ Best Paper
253BLA-Pose: Latent Action Pretraining Meets Pose Estimation
254AFreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Geometry-Complete 4D Reconstruction
254BFF3R: Feedforward Feature 3D Reconstruction from Unconstrained views
255ALong-Tail Internet Photo Reconstruction
255BFeedforward 3D Editing via Text-Steerable Image-to-3D
256ABalancing Local Geometry and Global Semantics in 3D Point Clouds with TAP-JEPA
256BEmergent Extreme-View Geometry in 3D Foundation Models
257ATrace Anything: Representing Any Video in 4D via Trajectory Fields
257BDream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
258ASafe2Drive: Evaluating Safe Driving Behaviors of E2E Autonomous Driving Models
258BSat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
259AGS4: Generalizable Sparse Splatting Semantic SLAM
259BSelf-Questioning Vision-Language Models: Reinforcement Learning for Compositional Visual Reasoning
260A3D Point World Models: Point Completion Enables More Accurate and Generalizable Dynamics Learning
260BAuditSplat: Self-Auditing Feed-Forward 3D Gaussian Splatting for Web-Scale Auto-Annotation
261AOutdoor-Targeted Perceptual Specialisation in 3DGS-MCMC via Late-Stage Anisotropic Primitive Splitting at Iso-Compute
261BAttDis & Friends: Three Lightweight Uncertainty Channels in Frozen Feed-Forward 3D Gaussian Splatting
262AChanges in Real Time: Online Scene Change Detection with Multi-View Fusion
262BLearning Surgical Robotic Manipulation with 3D Spatial Priors ⭐ Best Transitional
263AThe Epipolar Bottleneck: Minimal Sufficient Statistics for Sample-Efficient End-to-End 3D Reconstruction
263BSpectraSync: Differentiable Spectral Synchronization for End-to-End Multi-View 3D Reconstruction
264AThe Spectral Gap as a Geometric Prior: Laplacian-Biased Attention for End-to-End Multi-View 3D Reconstruction
264BGeometric Sufficiency: An Information-Theoretic Framework for Task-Aware 3D Representations
265AStreaming3D: Sequential 3D Generation via Evidential Memory
265BBenchmarking stereo reconstruction for 3D printable Martian terrain models
266ACellSplat: End-to-End 3D Gaussian Splatting for Cellular Decomposition of Spatial Transcriptomics