PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
hub Canonical reference
Nerf: Representing scenes as neural radiance fields for view synthesis
Canonical reference. 80% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 3
method 2
citation-polarity summary
representative citing papers
The paper introduces SP-VTP as a new setting for egocentric manipulation, releases the EgoSPT dataset with first-frame spatial annotations, and proposes the SPOT model that outperforms non-prompted baselines on cross-scene trajectory prediction.
Neural networks parameterize finite-rank generators for ODEs on the orthogonal Lie group, allowing optimization of orthonormal bases in function space with a universality result that rank-2 generators suffice for density.
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
Embedding Gaussian primitives into a ray tracing structure enables unified radio propagation simulation and view synthesis from visual-only reconstructions.
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
DiffSketcher synthesizes vector sketches from natural language by optimizing Bezier curves with diffusion model guidance via extended SDS loss.
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
RaPD enables resolution-agnostic image generation by diffusing in a semantics-enriched continuous Neural Image Field latent space using semantic guidance and a coordinate-queried attention renderer.
Aes3D creates the first 3D scene aesthetic assessment dataset and a model that regresses aesthetic scores from 3DGS representations alone.
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
DART adds differentiability to acoustic radiance transfer, enabling material optimization and improved performance on sparse acoustic field prediction tasks compared to signal processing and neural baselines.
HarmoGS adds semantic consistency-guided masking and dual-view orthogonal gradient harmonization to 3D Gaussian Splatting to reduce artifacts from distractors and cross-view illumination inconsistencies.
ODE-GS uses latent neural ODEs on Gaussian parameters to extrapolate dynamic 3D scenes, reporting 19.8% metric gains over baselines on D-NeRF, NVFi, and HyperNeRF.
citing papers explorer
-
Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
-
Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation
The paper introduces SP-VTP as a new setting for egocentric manipulation, releases the EgoSPT dataset with first-frame spatial annotations, and proposes the SPOT model that outperforms non-prompted baselines on cross-scene trajectory prediction.
-
Learning Orthonormal Bases for Function Spaces
Neural networks parameterize finite-rank generators for ODEs on the orthogonal Lie group, allowing optimization of orthonormal bases in function space with a universality result that rank-2 generators suffice for density.
-
The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
-
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
-
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
-
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
-
Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis
Embedding Gaussian primitives into a ray tracing structure enables unified radio propagation simulation and view synthesis from visual-only reconstructions.
-
What Cohort INRs Encode and Where to Freeze Them
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
-
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
DiffSketcher synthesizes vector sketches from natural language by optimizing Bezier curves with diffusion model guidance via extended SDS loss.
-
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
-
RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
RaPD enables resolution-agnostic image generation by diffusing in a semantics-enriched continuous Neural Image Field latent space using semantic guidance and a coordinate-queried attention renderer.
-
Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
Aes3D creates the first 3D scene aesthetic assessment dataset and a model that regresses aesthetic scores from 3DGS representations alone.
-
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
-
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
-
Differentiable Acoustic Radiance Transfer
DART adds differentiability to acoustic radiance transfer, enabling material optimization and improved performance on sparse acoustic field prediction tasks compared to signal processing and neural baselines.
-
HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
HarmoGS adds semantic consistency-guided masking and dual-view orthogonal gradient harmonization to 3D Gaussian Splatting to reduce artifacts from distractors and cross-view illumination inconsistencies.
-
ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
ODE-GS uses latent neural ODEs on Gaussian parameters to extrapolate dynamic 3D scenes, reporting 19.8% metric gains over baselines on D-NeRF, NVFi, and HyperNeRF.