REVIEW 21 cited by
WildGaussians: 3D Gaussian Splatting in the Wild
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
WildGaussians: 3D Gaussian Splatting in the Wild
read the original abstract
While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework.
Forward citations
Cited by 21 Pith papers
-
RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
RPC-GS enables native RPC-based rendering in Gaussian Splatting for satellite imagery by chaining geo-coordinate transformations and a Jacobian covariance projection, yielding lower reconstruction errors than perspect...
-
Relightable Gaussian Splatting for Virtual Production Using Image-Based Illumination
A relightable Gaussian Splatting method for virtual production decomposes scenes into fixed appearance and variable lighting by parameterizing primitives to directly sample high-resolution background textures, enablin...
-
Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction
ADM-GS decomposes static background appearance into traversal-invariant material and traversal-dependent illumination via a frequency-separated neural light field, yielding +0.98 dB PSNR gains and better cross-travers...
-
ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction
ProDiG progressively transforms aerial Gaussian splats into coherent ground-level 3D reconstructions via diffusion guidance and specialized attention modules.
-
UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing
Routing each 3D voxel to its most informative conditioning image via a model-intrinsic Voxel Reference Score unlocks robust unconstrained multi-image 3D generation without retraining.
-
SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization
A feed-forward Gaussian-splatting model that subdivides each primary Gaussian into learned sub-pixel primitives, achieving state-of-the-art high-resolution novel-view synthesis from low-resolution inputs.
-
Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
RefineSplat removes ambiguous distractors from 3DGS via entropy-aware adaptive masking and density control, releasing an 18-scene Ambiguous wild dataset and reporting SOTA metrics on multiple wild benchmarks.
-
Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
RefineSplat applies entropy-aware adaptive masking and density control to 3DGS to remove color- or semantically ambiguous distractors, validated on a new 18-scene Ambiguous wild dataset with claimed SOTA results.
-
Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication
Splaxel achieves up to 7.6x speedup in distributed 3DGS training on scenes with up to 120M Gaussians by using pixel-level communication and visibility prediction while preserving reconstruction quality.
-
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
EPS3D is an end-to-end architecture for 3D panoptic segmentation from multi-view images that uses distillation and semantic-instance mutual enhancement to achieve higher benchmark performance and speed than prior methods.
-
3D Skew Gaussian Splatting with Any Camera Trajectory Visualization Engine
3D Skew Gaussian Splatting extends standard 3D Gaussian Splatting with skew primitives, enhanced opacity, depth-aware densification, and a re-derived CUDA pipeline for a free-camera visualization engine.
-
HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
HarmoGS improves in-the-wild 3D Gaussian Splatting by using semantic consistency-guided masking and dual-view conflict-aware gradient harmonization to reduce artifacts from transient distractors and cross-view inconsi...
-
Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild
A new sparse-view 3D Gaussian splatting method for unconstrained scenes with distractors combines diffusion-based reference-guided refinement and sparsity-aware Gaussian replication to achieve better rendering quality.
-
DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures
DualSplat bootstraps object-level pseudo-masks from initial 3DGS reconstruction failures using residuals and SAM2 to enable robust second-pass optimization in transient-heavy scenes.
-
GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction
GA-GS uses motion segmentation, diffusion-based inpainting for pseudo-ground-truth, and per-Gaussian authenticity scalars to achieve SOTA static scene reconstruction from videos with dynamic occlusions.
-
FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting
FACT-GS allocates higher texture sampling density to high-frequency areas in 2D Gaussian Splatting through a learnable deformation field, recovering sharper details at the same parameter budget.
-
ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
A single shared Gaussian scaffold with per-period features and opacity gating reconstructs multi-period scenes better than static and dynamic baselines on a new 12-scene benchmark.
-
High Dynamic Range 3D Gaussian Splatting via Luminance-Chromaticity Decomposition
LCD-GS decouples luminance and chromaticity in 3D Gaussian Splatting to handle extreme radiance variations better than prior multi-exposure methods while using a simpler architecture.
-
One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
Given one RGB-D photo of an unseen object, an AI-generated 3D mesh, aligned jointly in metric scale and pose, yields state-of-the-art one-shot 6D pose estimation on YCBInEOAT, TOYL, and LM-O.
-
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.
-
Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with d...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.