ReConText3D is the first replay-memory framework for continual text-to-3D generation that prevents catastrophic forgetting on new textual categories while preserving quality on previously seen classes.
hub Mixed citations
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
Mixed citation behavior. Most common role is background (62%).
45
Pith papers citing it
Background
62% of classified citations
abstract
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.
hub tools
citation-role summary
background 5
method 2
baseline 1
citation-polarity summary
representative citing papers
CoGS is a compositional Gaussian splatting framework that decomposes monocular videos into human, object, and scene branches with a six-stage optimization to improve dynamic human-object scene reconstruction.
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toys4K in Chamfer and Hausdorff distances.
SplatShot is a training-free method that inserts per-step 3DGS refitting and photometric feedback into diffusion denoising to enforce multi-view consistency for single-photo 3D face avatars.
AdvScene is a scene-grounded evaluation method using Adversarial Patch-to-Scene Embedding (APSE) to map the operational envelope of physical adversarial patches in reconstructed real environments.
MVCHead uses a hierarchical state space model with bi-directional scans and an SE(3) critic to enforce 3D consistency in Gaussian avatars trained only on 2D images.
CAdam reinterprets densification in generative 3DGS as signal verification via gradient-moment interference, quantile context, and SNR gating to achieve large reductions in primitive count with comparable quality.
SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.
HairOrbit leverages video generation priors and a neural orientation extractor to achieve state-of-the-art strand-level 3D hair reconstruction from single-view portraits in visible and invisible regions.
THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.
VRGaussianAvatar enables real-time full-body 3D Gaussian Splatting avatars in VR from HMD tracking alone via inverse kinematics and binocular batching for efficient stereo rendering, outperforming mesh baselines in performance and user ratings.
SV-GS estimates a time-dependent skeleton pose plus fine deformations to enable 4D Gaussian splatting from sparse views, outperforming prior sparse methods by up to 34% PSNR on synthetic data and matching dense monocular baselines on real data with far fewer frames.
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
UniEdit-Flow presents tuning-free Uni-Inv and Uni-Edit methods for inversion and editing in flow models that achieve accurate reconstruction and robust region-preserving edits across generative models.
GenMF refines generated 3D meshes to encode appearance cues as geometry for monochromatic fabrication while minimizing fabrication stress.
DB-3DME supplies a human-rated 3D mesh dataset and shows that fine-tuning the visual encoder of Qwen-2.5-VL-7B produces automatic evaluations that align better with humans than prior VLMs.
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
PhyGenHOI couples a motion diffusion model for humans with material point method simulation for objects on 3D Gaussians, using attraction loss, contact re-simulation, and masked video-SDS to produce physically consistent dynamic interactions from text.
Stream3D is a training-free method that maintains a fixed-size evidential memory of past frames to convert frozen view-conditioned 3D generators into consistent streaming generators.
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
REVIVE 3D generates voluminous 3D assets from flat 2D images via an inflated prior construction followed by latent-space refinement, plus new metrics for volume and flatness validated by user study.
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.
citing papers explorer
-
HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
HairOrbit leverages video generation priors and a neural orientation extractor to achieve state-of-the-art strand-level 3D hair reconstruction from single-view portraits in visible and invisible regions.
-
HOIGS: Human-Object Interaction Gaussian Splatting
HOIGS adds a cross-attention HOI module to Gaussian Splatting that combines HexPlane human features with Cubic Hermite Spline object features to model interaction-induced deformations.