ResiHMR is the first single-image system to explicitly reconstruct residual-limb surfaces and perform topology-adaptive optimization for people with limb loss.
Nerf: Representing scenes as neural radiance fields for view syn- thesis.Communications of the ACM, 65(1):99–106
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 3polarities
background 3representative citing papers
Pretraining on 1M wild videos followed by post-training on curated data yields high-fidelity feedforward 3D avatars that generalize across identities, clothing, and lighting with emergent relightability and loose-garment support.
TranSplat performs instant object relighting in Gaussian Splatting by analytically modulating SH appearance coefficients via per-normal irradiance ratios from source and target environment maps, with dual-path specularity handling and SH self-shadowing.
A Transformer-based UV feature predictor followed by detail enhancement generates consistent 3D Gaussian heads from sketches, with mask fusion enabling real-time free-viewpoint edits.
A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
A semantic feature optimization grounds disconnected partial 3D reconstructions to geospatially accurate reference models derived from Google Earth, improving global alignment across classical and learning-based pipelines.
citing papers explorer
-
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
ResiHMR is the first single-image system to explicitly reconstruct residual-limb surfaces and perform topology-adaptive optimization for people with limb loss.
-
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Pretraining on 1M wild videos followed by post-training on curated data yields high-fidelity feedforward 3D avatars that generalize across identities, clothing, and lighting with emergent relightability and loose-garment support.
-
TranSplat: Instant Object Relighting in Gaussian Splatting via Spherical Harmonic Radiance Transfer
TranSplat performs instant object relighting in Gaussian Splatting by analytically modulating SH appearance coefficients via per-normal irradiance ratios from source and target environment maps, with dual-path specularity handling and SH self-shadowing.
-
SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
A Transformer-based UV feature predictor followed by detail enhancement generates consistent 3D Gaussian heads from sketches, with mask fusion enabling real-time free-viewpoint edits.
-
Visually-grounded Humanoid Agents
A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
-
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
-
Scene Grounding In the Wild
A semantic feature optimization grounds disconnected partial 3D reconstructions to geospatially accurate reference models derived from Google Earth, improving global alignment across classical and learning-based pipelines.