Tracker is a self-supervised VL tracker that uses a Dynamic Token Aggregation Module to learn instance tracking from single language descriptions in unlabeled videos and outperforms prior self-supervised methods.
hub
High-resolution image synthesis with latent diffusion models
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
C-GenReg achieves training-free 3D point cloud registration by generating multi-view-consistent images from geometry, extracting VFM correspondences, and probabilistically fusing them with raw geometric matches for zero-shot performance on indoor and outdoor benchmarks.
NeuroFlow is the first unified flow model for bidirectional visual encoding and decoding from neural activity using NeuroVAE and cross-modal flow matching.
VOSR shows that competitive generative image super-resolution with faithful structures can be achieved by training a diffusion-style model from scratch on visual data alone, using a vision encoder for guidance and a restoration-oriented sampling strategy.
MultiAnimate adds Identifier Assigner and Identifier Adapter modules to diffusion video models so they can handle multiple characters without identity mix-ups, generalizing from two-character training data to more characters.
ATATA enables fast joint inference of structurally aligned pairs using Rectified Flow models via segment transport, improving state-of-the-art for image and video generation while matching 3D quality at much higher speed.
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
GOR-IS removes objects from 3D Gaussian Splatting reconstructions by performing inpainting in an intrinsic decomposition space that explicitly models light transport for consistent global lighting and non-Lambertian surfaces.
EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
A technique reconstructs large urban areas from sparse extreme off-nadir satellite images by modeling geometry as a Z-monotonic 2.5D height map SDF and applying a generative network to restore plausible textures on the resulting mesh.
LEMUR 2 releases a multi-generator, multi-task neural-architecture corpus with real-device latency metadata intended as fuel for LLM-driven AutoML.
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
Proposes TCD, a three-step conditional diffusion model with ICD module, claiming superior fidelity and generalization for LFM 3D reconstruction.
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
A part-wise semi-autoregressive discrete diffusion model for point-cloud-to-mesh generation that separates global structure from local detail, beating prior SOTA on Objaverse.
Adaptive Head Synthesis (AHS) employs head-reenacted synthetic data augmentation to enable robust head swapping on full upper-body images without paired training data.
citing papers explorer
-
Learning to Track Instance from Single Nature Language Description
Tracker is a self-supervised VL tracker that uses a Dynamic Token Aggregation Module to learn instance tracking from single language descriptions in unlabeled videos and outperforms prior self-supervised methods.
-
C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
C-GenReg achieves training-free 3D point cloud registration by generating multi-view-consistent images from geometry, extracting VFM correspondences, and probabilistically fusing them with raw geometric matches for zero-shot performance on indoor and outdoor benchmarks.
-
NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
NeuroFlow is the first unified flow model for bidirectional visual encoding and decoding from neural activity using NeuroVAE and cross-modal flow matching.
-
VOSR: A Vision-Only Generative Model for Image Super-Resolution
VOSR shows that competitive generative image super-resolution with faithful structures can be achieved by training a diffusion-style model from scratch on visual data alone, using a vision encoder for guidance and a restoration-oriented sampling strategy.
-
MultiAnimate: Pose-Guided Image Animation Made Extensible
MultiAnimate adds Identifier Assigner and Identifier Adapter modules to diffusion video models so they can handle multiple characters without identity mix-ups, generalizing from two-character training data to more characters.
-
ATATA: One Algorithm to Align Them All
ATATA enables fast joint inference of structurally aligned pairs using Rectified Flow models via segment transport, improving state-of-the-art for image and video generation while matching 3D quality at much higher speed.
-
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
-
GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space
GOR-IS removes objects from 3D Gaussian Splatting reconstructions by performing inpainting in an intrinsic decomposition space that explicitly models light transport for consistent global lighting and non-Lambertian surfaces.
-
EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure
EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
-
From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images
A technique reconstructs large urban areas from sparse extreme off-nadir satellite images by modeling geometry as a Z-monotonic 2.5D height map SDF and applying a generative network to restore plausible textures on the resulting mesh.
-
LEMUR 2: Unlocking Neural Network Diversity for AI
LEMUR 2 releases a multi-generator, multi-task neural-architecture corpus with real-device latency metadata intended as fuel for LLM-driven AutoML.
-
Bridging Video Understanding and Generation in a Unified Framework
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
-
Three-Step Conditional Diffusion 3D Reconstruction for Light-Field Microscopy
Proposes TCD, a three-step conditional diffusion model with ICD module, claiming superior fidelity and generalization for LFM 3D reconstruction.
-
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
-
PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion
A part-wise semi-autoregressive discrete diffusion model for point-cloud-to-mesh generation that separates global structure from local detail, beating prior SOTA on Objaverse.
-
AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
Adaptive Head Synthesis (AHS) employs head-reenacted synthetic data augmentation to enable robust head swapping on full upper-body images without paired training data.