Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks70 from public data
- Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model641
Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view, is reported, and the feasibility of training a ControlNet on Zero123++ for enhanced control over the generation process is showcased.
- OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations182
This work introduces OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources, including academic papers, textbooks, and more challenging cases such as handwritten notes and densely typeset newspapers, and sets a new standard for the fair, diverse, and fine-grained evaluation in document parsing.
- Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping74
This paper proposes an effective end-to-end unified framework to achieve both face reenactment and swapping, and sufficiently transfers identity and attribute based on learned disentangled representations to generate high-fidelity faces.
- OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text60
This paper introduces OmniCorpus, a 10 billion-scale image-text interleaved dataset that has 15 times larger scales while maintaining good data quality and is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs.
- 50
- Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification36
This paper proposes a specular reflection detection and removal method that can effectively detect the specular regions in endoscopic images of different brightness and can improve the operating efficiency of the algorithm while restoring the texture structure information of the high-resolution image.
- Computerized tongue image segmentation via the double geo-vector flow29
A double geo-vector flow (DGF) was proposed to detect the tongue edge and segment the tongue region in the image, such that the geodesic flow was evaluation in the lower part, and the geo-gradient vector flow was evaluated in the upper part.
- 29
- 26
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio25
This paper abstracts the process of people hearing speech, extracting meaningful cues, and creating vari-ous dynamically audio-consistent talking faces, termed Lis-tening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio, and intro-duce the Controllable Coherent Frame generation.
- Continuous Implicit SDF Based Any-Shape Robot Trajectory Optimization25
Simulation and real-world experiments validate the high performance of the proposed trajectory optimization pipeline applicable to the implicit SDF, which guarantees continuous collision evaluation even for nonconvex robots with complex surfaces.
- Live shopping interactivity, social presence and sustainable consumer purchase intention: Based on TAM model21
The empirical results show that interactivity has a significant positive effect on purchase intention, and social presence, perceived ease of use and perceived usefulness play a mediating role in the process of interactivity affecting purchase intention.
- 20
- Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator17
This work derives a novel paradigm free of unstable seesaw-style optimization, resulting in simple, stable, and effective training and inference schemes, and adopts the Diffusion Models.
- EIEN: Endoscopic Image Enhancement Network Based on Retinex Theory17
The experimental results show that EIEN enhances the brightness and contrast of endoscopic images and highlights vascular and tissue information and obtained the best results in terms of visual perception and objective evaluation.
- An Endoscope Image Enhancement Algorithm Based on Image Decomposition14
A new endoscopic image enhancement algorithm that can effectively highlight the blood vessel information in endoscopic images while avoiding the influence of noise and highlight points is proposed and compared with six other algorithms in the laboratory dataset.
- RETRACTED ARTICLE: Immersive animation scene design in animation language under virtual reality13
The results show that in the design of an immersive VR scene, the relative moving speed of the forward straight line should be maintained less than 6.5 times of the audience’s perceived speed, and the optimal relative moving speeds of the scene should be kept below 5 times of that of the viewers’ perceived speed when they moving backward.
- Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition11
This paper decomposes the mel-spectrogram into three distinct types of signals, employing quantization or continuity to them, and shows how to balance the representation of mel-spectrograms in terms of completeness and complexity through a new approach called Mel Quantization-Continuum Decomposition (Mel-QCD).
- 11
- Vague C-means clustering algorithm11
This paper introduces a fuzzy clustering algorithm in the context of VSs theory and fuzzy C-means clustering (FCM) and proposes the QPSO (quantum-behaved particle swarm optimization)-based VCM calculation, which is more effective and more efficient than FCM and three varieties of FCM.
- TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On10
This work decouple clothing identity into fine-grained factors: style for color and category information, texture for high-frequency details, and structure for smooth spatial adaptive transformation and introduces the training-free T-RePaint strategy to further enhance clothing identity preservation while maintaining the realistic try-on effect during the inference.
- Robust Soliton Distribution-Based Zero-Watermarking for Semi-Structured Power Data9
Experimental and simulation validation demonstrates that this method, while ensuring data security, achieves a zero-watermark extraction success rate exceeding 98% and holds significant application value for data monitoring and anomaly tracking in power systems.
- The improved deep plug-and-play super-resolution with residual-in-residual dense block for arbitrary blur kernels7
The RRDB is adopted to replace the deep feature extraction part in DPSR in order to extract abundant local features, which makes the network capacity higher benefiting from the dense connections, and the residual learning in different levels in RRDB can obtain high quality images.
- Cervical Precancerous Lesion Image Enhancement Based on Retinex and Histogram Equalization7
The proposed enhancement algorithm based on retinex and histogram equalization has shown superior performance compared to other traditional methods based on objective indicators such as peak signal-to-noise ratio, detail-variance–background-Variance, gray square mean deviation, contrast improvement index, and enhancement quality index.
- 7
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 2026-10-15. 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.