NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
Seg4diff: Unveiling open-vocabulary segmentation in text-to-image diffusion transformers
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CV 7roles
extension 1polarities
extend 1representative citing papers
TORA distills topological structure from pretrained 3D encoders into flow-matching backbones via cosine matching and CKA loss, delivering up to 6.9x faster convergence and better accuracy on 3D shape assembly benchmarks with zero inference overhead.
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
Copy-move forgeries induce detectable spectral shifts in the normalized Laplacian of self-attention graphs from Stable Diffusion U-Nets, identifiable via Wasserstein distance to authentic reference spectra.
Entropy-gradient grounding uses model uncertainty to retrieve evidence regions in VLMs, improving performance on detail-critical and compositional tasks across multiple architectures.
C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.
citing papers explorer
-
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
-
TORA: Topological Representation Alignment for 3D Shape Assembly
TORA distills topological structure from pretrained 3D encoders into flow-matching backbones via cosine matching and CKA loss, delivering up to 6.9x faster convergence and better accuracy on 3D shape assembly benchmarks with zero inference overhead.
-
Diffusion Model as a Generalist Segmentation Learner
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
-
Spectral Forensics of Diffusion Attention Graphs for Copy-Move Forgery Detection
Copy-move forgeries induce detectable spectral shifts in the normalized Laplacian of self-attention graphs from Stable Diffusion U-Nets, identifiable via Wasserstein distance to authentic reference spectra.
-
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
Entropy-gradient grounding uses model uncertainty to retrieve evidence regions in VLMs, improving performance on detail-critical and compositional tasks across multiple architectures.
-
C3G: Learning Compact 3D Representations with 2K Gaussians
C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.
- Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers