Solv3R looped transformer solves multi-view geometry
Solv3R uses a looped transformer for iterative refinement in multi-view reconstruction without task-specific modules.
Stories per day · 30 days
3 RSS
Related3d-world-models2waymo23d-mapping13d-reconstruction1autonomous-driving1benchmark1computer-vision1diffusion1image-generation1kitti1lidar1neural-implicit1nuscenes1object-insertion1signed-distance-field1transformer1world-model1
8 stories, newest first · one card per story
Stories tagged #geometry
PhysInsert inserts objects with geometry and scene interaction
The authors built Insert World and PhysInsert-Bench and report better fidelity plus a user study on placement and lighting.
Neural energy regularization smooths LiDAR maps without extra inference cost
Curvature energy on neural signed-distance level sets reduces jitter on million-point maps while keeping geometric fidelity.
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
GeoState decouples scene geometry from camera motion for predictive 3D world modeling.
GeoState separates scene geometry from camera motion in 3D world models
Predicted states can be decoded under predicted or specified cameras without per-frame scale alignment.
Octrees as an Explicit 3D Language
OctLLM feeds 3D shapes to an LLM as sparse octree tokens via frozen-backbone trainable branches, cutting image-to-3D FID 17.4% versus ShapeLLM-Omni.
Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation
GEAR uses geometry to route attention to visual memory for long camera-controlled video generation.
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
GAE learns a compact geometry-native latent that improves 3D-consistent video and world generation.