REVIEW 14 cited by
Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed. We introduce Street Gaussians, a new explicit scene representation that tackles these limitations. Specifically, the dynamic urban scene is represented as a set of point clouds equipped with semantic logits and 3D Gaussians, each associated with either a foreground vehicle or the background. To model the dynamics of foreground object vehicles, each object point cloud is optimized with optimizable tracked poses, along with a 4D spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of object vehicles and background, which in turn allows for scene editing operations and rendering at 135 FPS (1066 $\times$ 1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets. The code will be released to ensure reproducibility.
Forward citations
Cited by 14 Pith papers
-
DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
A simulation framework that combines 3D Gaussian Splatting with MuJoCo reports improved zero-shot transfer of manipulation policies from simulation to real robots.
-
GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting
A camera-only Gaussian-surfel pipeline reconstructs full Waymo scenes, converts them to binary occupancy labels, and trains CVT-Occ to generalize on Occ3D-Waymo and Occ3D-nuScenes at a level close to or above LiDAR-la...
-
RemVerse: Supporting Reminiscence Activities for Older Adults through AI-Assisted Virtual Reality
An AI-assisted VR environment with generative visuals and a dialogue agent helped 14 older adults recall, visualize, and elaborate personal memories, with engagement increasing over a single session.
-
InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
InstaScene combines Gaussian-based instance decomposition with generative completion to produce complete, scene-aligned 3D object models from cluttered scenes.
-
VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
A training-only Gaussian splatting loss, which renders predicted 3D semantics and motion into 2D camera views, improves semantic occupancy and scene flow prediction across several camera-based models.
-
RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes
RadarSplat brings Gaussian Splatting to automotive radar, explicitly modeling multipath and receiver noise to synthesize realistic radar images and estimate occupancy.
-
SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
SynthDrive automatically mines images of rare objects, reconstructs them as 3D assets from a single view, and synthesizes driving footage that modestly improves detection of those objects.
-
Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
MultiTrust-X is a new 32-task, 28-dataset benchmark over 30 multimodal LLMs claiming that trustworthiness lags capability, that multimodality amplifies base-model risks, and that its RESA alignment method reaches stat...
-
ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
A diffusion-enhanced 3D scene-reconstruction simulator plus adversarial and trajectory-diversity modules reduces collision rate of an end-to-end RL driving policy in closed-loop tests.
-
Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
A split-then-clone densification schedule with energy-guided multi-resolution training roughly halves 3D Gaussian Splatting training time while keeping reconstruction quality.
-
CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting
CRUISE reconstructs real V2X driving scenes as editable Gaussians, then shows that training on its generated data improves 3D detection and tracking on the V2X-Seq benchmark.
-
EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
A Real2Sim2Real framework that aligns simulator dynamics via differentiable parameter fitting and renders photorealistic policy-training videos with a diffusion model, improving real-world manipulation success.
-
OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving
Adding object-centric radiance-field rendering and height-aware opacity attention to the DualBEV detector improves camera-only 3D object detection on nuScenes by up to 2.0 mAP points.
-
DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion
DriveGen3D makes long driving-video synthesis and 3D scene reconstruction practical by caching only the conditional diffusion branch, quantizing cross-view attention, and fusing temporal context into a feed-forward Ga...
Discussion (0). Sign in to comment.