REVIEW 6 cited by
Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review
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
Signed reviews
read the original abstract
This review thoroughly examines the role of semantically-aware Neural Radiance Fields (NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It explores how NeRFs adeptly infer 3D representations for both stationary and dynamic objects in a scene. This capability is pivotal for generating high-quality new viewpoints, completing missing scene details (inpainting), conducting comprehensive scene segmentation (panoptic segmentation), predicting 3D bounding boxes, editing 3D scenes, and extracting object-centric 3D models. A significant aspect of this study is the application of semantic labels as viewpoint-invariant functions, which effectively map spatial coordinates to a spectrum of semantic labels, thus facilitating the recognition of distinct objects within the scene. Overall, this survey highlights the progression and diverse applications of semantically-aware neural radiance fields in the context of visual scene interpretation.
Forward citations
Cited by 6 Pith papers
-
Exploring Active Learning for Label-Efficient Training of Semantic Neural Radiance Field
Active learning with a 3D spatial-diversity term cuts annotation cost by over 2x for semantically-aware NeRF training versus random sampling.
-
OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness
OC-SOP fuses object detection queries into a semantic occupancy completion U-Net, improving foreground-object voxel accuracy and achieving state-of-the-art mIoU on SemanticKITTI.
-
GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes
GSsplat is a feed-forward generalizable 3D Gaussian Splatting model that renders novel-view colors and semantic maps from multi-view inputs without per-scene training, claiming state-of-the-art semantic accuracy at th...
-
EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction
A masked fine-tuned diffusion model simultaneously completes occluded views and synthesizes novel viewpoints, enabling fast feed-forward 3D reconstruction.
-
RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation
RAZER fuses online TSDF reconstruction with open-vocabulary instance embeddings and tracking to produce real-time, queryable 3D semantic maps without any 3D training.
-
Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation
LBG segments 3D Gaussian Splatting scenes into objects, parts, and subparts by assigning each pixel's maximum-contributing Gaussian a 2D mask ID and merging fragments across frames using geometric and semantic similarity.
Discussion (0). Continue with ORCID to comment.