Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks19 from public data
- 52
- 39
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- 30
- TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model17
A novel approach is proposed that integrates topological constraints into a diffusion model to improve the generation of realistic, contextually accurate cell topologies and introduces a new metric, Topological Fréchet Distance (TopoFD), which overcomes the limitations of traditional metrics like FID in evaluating topological structure.
- Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models17
A novel plug-and-play method SingDiffusion is proposed to address the initial singular time step sampling, which not only effectively resolves the average brightness issue for a wide range of diffusion models without extra training efforts, but also enhances their generation capability in achieving notable lower FID scores.
- 5
- Local Bidirection Recurrent Network for Efficient Video Deblurring with the Fused Temporal Merge Module5
This work adopts the recurrent-based method as the baseline and reconsider the recurrent mechanism as well as the temporal feature alignment in the state-of-the-art methods, and adds the local backward connection to the global forward recurrent backbone to effectively exploit accurate future information.
- 5
- DiHuR: Diffusion-Guided Generalizable Human Reconstruction3
DiHuR is introduced, a novel Diffusion-guided model for generalizable Human 3D Reconstruction and view synthe-sis from sparse, minimally overlapping images that integrates two key priors in a coherent manner: the prior from generaliz-able feed-forward models and the 2D diffusion prior.
- Implementation of SDTV Video Encoder with Real-Time Constant and Variable Bit-Rate Control2
This paper suggests an implementation procedure of an SDTV video encoder and proposes a novel VBR bit-allocation strategy that could be implemented in this encoder system and experimental results demonstrate that the proposed VBR encoder displays a better performance than the CBR encoder.
- 1
- 1
- Code rate control for motion JPEG2000 based on interframe correlation1
Experi-ments show that for encoding the test sequence under 1.2bit per pixel, the passes which need coding had been decreased about 52.3% on the average comparing with PCRD while the difference of images quality between them is about 0.0553dB.
- A Honeycomb Shape Localization Algorithm Based on Levy-PSO–
A honeycomb shape localization algorithm based on Levy-PSO that could improve the positioning accuracy and slow speed of convergence in order to have better stability in Wireless Sensor Networks.
- Frame Rate Up-conversion Algorithm Based on Motion Similarity Constrain–
A novel video frame rate-up conversion algorithm based on motion similarity constrain is proposed that adopts block motion vector refinement based on similar factor to reduce block artifacts, and a variable weighted-window overlapped block compensated interpolation to improve the quality of image.
- Design of AVS Fast Mode Decision Based on Image Block Row/Column Pipeline–
A design of fast mode decision based on image block row/column pipeline is provided according to the features and dependence of different modes in AVS to minimize the idle cycle of all the processing modules in the pipeline.
- An Improved SROD Blotch Detection Method in Old Film–
Experimental results show that the blotch detection method proposed in this paper is effective and can be easily implemented.
- Color C-V Method and Its Application in Segmentation of Halftone Image–
A color C-V method which makes sufficient use of color information in images so that it segments color images efficiently is proposed, and considering the characteristics of human vision, chooses the appropriate color space.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. 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. You will be asked to sign in.