Click3R corrects stereo 3D reconstruction with sparse clicks
A lightweight adapter uses user point correspondences, and the authors say one click can cut reconstruction error.
Stories per day · 30 days
4 RSS
Relatedcomputer-vision4gaussian-splatting2scene-generation2agentic-systems1camera-trajectory1click3r1computer-graphics1dynamic-scenes1egocentric-video1geometric-composition1geometry1human-in-the-loop1mesh1novel-view-synthesis1point-cloud1pose-graph1probing1robotics1
25 stories, newest first · one card per story
Stories tagged #3d-reconstruction
Solv3R looped transformer solves multi-view geometry
Solv3R uses a looped transformer for iterative refinement in multi-view reconstruction without task-specific modules.
AnchorComplete recovers complete scene meshes from partial point clouds
AnchorComplete reconstructs complete scene meshes from partial point clouds using partial-point conditioning and metric-scale coarse-to-fine generation.
Hexels use hexagonal primitives for more efficient 3D scene rendering
Across 34 scenes, Hexels beat memory-matched 2DGS by 4.53-7.38 dB PSNR with lower training VRAM.
Linear probe predicts VGGT pose failures the model does not report
On HardMatch, where VGGT fails on 35% of 1,000 pairs, a frozen-feature probe reaches 93.5% ROC-AUC.
Easy-3Dfy composes object meshes into single-image 3D scenes
An RPF aligner matches object-local meshes to partial scene pointmaps without full scene supervision.
HiP3R aligns long video 3D reconstructions with hierarchical pose graphs
A chunk-level Sim(3) graph sets global scale, then one shared SE(3) camera is estimated per frame, with no extra training.
SceneRig builds simulation-ready 3D scenes from single images
An agent edits and validates scenes in a physics simulator so reconstructed objects stay physically stable.
EgoXperience learns world-grounded egocentric video reconstruction
EgoX cuts camera, hand, and depth errors by 68.9%, 65.6%, and 42.9% versus the strongest baselines.
Gaussian allocation methods recover fading dynamic content in volumetric video
Seed Injection and Temporal Biased Relocation keep a fixed Gaussian budget while recovering small, fast-moving objects.
Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving
Drive3R streams block-wise 3D reconstruction for driving and sets new nuScenes, KITTI, and Waymo results.
GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
NVIDIA researchers introduced GATOR, which reconstructs textured, scene-aligned 3D objects from one or more casual images.
Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery
JoHan recovers smoother 2D and 3D hand motion directly from video without per-frame pose estimates.
Optimization Encoders: Rethinking Second-Order Meta-Learning for Neural Fields
MetaLF frames latent optimization as an encoder for second-order meta-learning of conditional neural fields.
AI agents build 3D scenes from photos but have no idea if they got it right
LEGO-Anything has coding agents write Blender scenes from one photo, but they cannot reliably judge geometric accuracy.
10
T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
T3lescope reconstructs high-fidelity 3D meshes from multi-view images at arbitrary scale without per-scene optimization.
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
LEGO-Anything uses coding agents to rebuild editable 3D scenes as executable Blender programs.
Information Blackhole: Exploring Backdoor Mechanism in 3D Point Cloud Reconstruction
Researchers show point-cloud autoencoder backdoors leak source geometry and propose Gaussian constraints to control them.
SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning
SpatialSpeak pretrains vision-language models on multi-view reconstruction, reaching a 62.8 ReVSI spatial-reasoning score.
OC-GS: Gaussian Splatting for Irregular Turntable Capture
OC-GS refines per-image angles in a shared orbit model to reconstruct objects from sparse, irregular turntable views.
HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis
HARMONY reconstructs indoor 3D scenes from one image using hierarchical agentic reasoning and geometry refinement.
NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction
NeuSOGA3D combines learned perception with symbolic spline reasoning to produce explainable, CAD-compatible 3D reconstructions from point clouds across all forty ModelNet40 categories.
Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction
MarkTechPost tutorial implements a hierarchical NeRF in JAX using jax3d volume-rendering primitives for novel-view synthesis and 3D reconstruction.
2
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
RCWM reconstructs complex 3D worlds as executable code from a single image using recursive scene programs with global-local-global solver recursion.