Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks48 from public data
- Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation372
This paper is the first to propose a hybrid model, dubbed as Show-1, which marries pixel-based and latent-based VDMs for text-to-video generation and achieves state-of-the-art performance on standard video generation benchmarks.
- DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes151
DeVRF, a novel representation to accelerate learning dynamic radiance fields via utilizing the 3D volumetric canonical space learnt from multi-view static images to ease the learning of 4D voxel deformation field with only few-view dynamic sequences is presented.
- VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence81
This work introduces the Video Swap framework that exploits semantic point correspondences, inspired by the observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape.
- Instant3D: Instant Text-to-3D Generation64
A novel framework for fast text-to-3D generation, dubbed Instant3D, that is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network.
- MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation63
This work introduces MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline that can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness.
- 63
- 42
- HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video38
HOSNeRF is introduced, a novel 360° free-viewpoint rendering method that reconstructs neural radiance fields for dynamic human-object-scene from a single monocular in-the-wild video that significantly outperforms SOTA approaches on two challenging datasets by a large margin.
- 33
- Exocentric-to-Egocentric Video Generation28
This work designs an exocentric-to-egocentric view translation prior to provide spatially aligned egocentric features as a concatenation guidance for the input of egocentric video diffusion model, and introduces the temporal attention layers into the egocentric video diffusion pipeline to improve the temporal consistency cross egocentric frames.
- DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing28
This work proposes the image-based video-NeRF editing pipeline with a set of innovative designs, including multi-view multi-pose Score Distillation Sampling (SDS) from both the 2D personalized diffusion prior and 3D diffusion prior, reconstruction losses, text-guided local parts super-resolution, and style transfer.
- 24
- X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model24
X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules to work directly with the upgraded text-to-image diffusion model without further retraining, is introduced and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.
- I2VControl: Disentangled and Unified Video Motion Synthesis Control22
This paper proposes a spatial partitioning strategy, where each unit is assigned to a concomitant control category, enabling diverse control types to be dynamically orchestrated within a single synthesis pipeline without conflicts.
- Learning Code Preference via Synthetic Evolution22
This paper proposes CodeFavor, a framework for training pairwise code preference models from synthetic evolution data, including code commits and code critiques, and introduces CodePrefBench, a benchmark comprising 1364 rigorously curated code preference tasks to cover three verifiable properties-correctness, efficiency, and security-along with human preference.
- 20
- Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving13
This work proposes a novel task, called generalized few-shot 3D object detection, where the authors have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes, and proposes a sample adaptive balance loss to alleviate the issue of long-tailed data distribution in autonomous driving scenarios.
- 13
- 10
- ColonNeRF: High-Fidelity Neural Reconstruction of Long Colonoscopy10
This work introduces a new reconstruction framework based on neural radiance field (NeRF), named ColonNeRF, which leverages neural rendering for novel view synthesis of long-sequence colonoscopy and outperforms existing methods on two benchmarks over four evaluation metrics.
- 9
- 9
- 8
- 7
- 7
- Exploiting Multi-Direction Features in MRF-Based Image Inpainting Approaches7
Experimental results show that the proposed Structure Offsets Statistics based image inpainting algorithm is superior to several state-of-the-art approaches in terms of the abilities of maintaining structure coherence and neighborhood consistence and the computational efficiency.
- 6
- 6
- Generalised Co-Salient Object Detection6
A novel random sampling based Generalised CoSOD Training (GCT) strategy to distill the awareness of inter-image absence of co-salient objects into coSOD models by allowing the presence of "noisy images" which do not show the shared co-Salient object.
- 5
- 5
- 4
- Quantum representation and geometric transformation of 3D images4
A quantum image representation adapted to three-dimensional images is proposed based on the novel enhanced quantum representation for quantum image and the Fourier transform representation, which allows for more precise encoding of image position information and reduces data loss.
- LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras4
An efficient paradigm (LF Tracy) is proposed that surpasses the existing state-of-the-art method through extensive experiments and demonstrates a 23% improvement over previous results on the latest large-scale PKU dataset.
- 4
- 3
- 3
- 2
- 2
- Advanced Center-Folding based Reversible Hiding Scheme with Pixel Value Ordering2
This study uses the center folding strategy to fold the secret message and embed them separately into two stego-images and uses the pixel value ordering method to increase the embedding capacity in the image.
- 1
- 1
- –
- –
- –
- Adaptive weighted aggregation federated learning algorithm based on dual regularization–
Experimental results show that the method proposed in this paper can enhance the generalization ability of the global model on different datasets and neural networks, and outperforms the baseline federated learning method in non-IID setting.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.