A two-stage flow-matching model that seeds point-cloud generation from a generated BEV density map, using teacher-estimated point pairings to keep transport paths straight, achieves SOTA JSD/IoU on SemanticKITTI completion and best COV on KITTI-360.
Semantic scene completion from a single depth image
4 Pith papers cite this work, alongside 43 external citations. Polarity classification is still indexing.
4
Pith papers citing it
43
external citations · Pith
abstract
This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-view depth map observation. Previous work has considered scene completion and semantic labeling of depth maps separately. However, we observe that these two problems are tightly intertwined. To leverage the coupled nature of these two tasks, we introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the camera view frustum. Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning. To train our network, we construct SUNCG - a manually created large-scale dataset of synthetic 3D scenes with dense volumetric annotations. Our experiments demonstrate that the joint model outperforms methods addressing each task in isolation and outperforms alternative approaches on the semantic scene completion task.
representative citing papers
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
A single RGB image is converted into a coherent 3D scene by denoising all object poses and shapes simultaneously with a diffusion model.
FreeOcc enables training-free open-vocabulary 3D occupancy prediction from RGB-D sequences by combining SLAM, dense Gaussian maps, off-the-shelf vision-language models, and probabilistic projection, achieving over 2x gains on benchmarks and zero-shot transfer to novel scenes.
citing papers explorer
-
FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows
A two-stage flow-matching model that seeds point-cloud generation from a generated BEV density map, using teacher-estimated point pairings to keep transport paths straight, achieves SOTA JSD/IoU on SemanticKITTI completion and best COV on KITTI-360.
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
Coherent 3D Scene Diffusion From a Single RGB Image
A single RGB image is converted into a coherent 3D scene by denoising all object poses and shapes simultaneously with a diffusion model.
-
FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction
FreeOcc enables training-free open-vocabulary 3D occupancy prediction from RGB-D sequences by combining SLAM, dense Gaussian maps, off-the-shelf vision-language models, and probabilistic projection, achieving over 2x gains on benchmarks and zero-shot transfer to novel scenes.