arXiv subjects

Chun-Hung Wu

Publications and source records attributed to Chun-Hung Wu.

6 recordsLinked to original sources

arXiv2026

JOMP: Jointly-Optimized Mixed-Precision Quantization Across Neural Video Coding Frameworks and Buffering Strategies

Variational autoencoder-based neural video coding has demonstrated impressive rate-distortion performance. However, its adoption in real-world applications remains hindered by challenges, such as prohibitively high computational complexity and limited cross-platform interoperability. These issues are often overlooked, as most neural video codecs rely on floating-point arithmetic to fully explore their rate-distortion potential. Practical deployment, however, requires integer-based implementations. Converting floating-point implementations into integer-based networks is non-trivial, since it involves quantizing inter-dependent coding components, whose sensitivity to precision may vary across codec designs. This paper introduces a Jointly-Optimized Mixed-Precision (JOMP) framework, in which both quantization parameters and bit widths are treated as learnable variables during training. This enables different codec modules to operate at varying precision levels, thereby jointly optimizing the rate-distortion-complexity trade-off. To the best of our knowledge, JOMP is the first mixed-precision quantization framework for neural video codecs. Its effectiveness is validated through a systematic investigation of quantization across different coding frameworks and temporal buffering strategies. Our study marks the first attempt to a unified understanding of the combined effects of modern coding frameworks and temporal buffering strategies, with the aim of informing future development of neural video codecs from a practicality perspective. In addition, we develop a complete integerization pipeline to achieve deterministic decoding. Overall, when applied to our best-performing model, JOMP enables end-to-end mixed-precision learning for integer neural video codecs, achieving rate-distortion performance comparable to that of the state-of-the-art DCVC-FM while reducing bit operations by 87.6%.

eess.IV↗

arXiv2025

HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding

Most frame-based learned video codecs can be interpreted as recurrent neural networks (RNNs) propagating reference information along the temporal dimension. This work revisits the limitations of the current approaches from an RNN perspective. The output-recurrence methods, which propagate decoded frames, are intuitive but impose dual constraints on the output decoded frames, leading to suboptimal rate-distortion performance. In contrast, the hidden-to-hidden connection approaches, which propagate latent features within the RNN, offer greater flexibility but require large buffer sizes. To address these issues, we propose HyTIP, a learned video coding framework that combines both mechanisms. Our hybrid buffering strategy uses explicit decoded frames and a small number of implicit latent features to achieve competitive coding performance. Experimental results show that our HyTIP outperforms the sole use of either output-recurrence or hidden-to-hidden approaches. Furthermore, it achieves comparable performance to state-of-the-art methods but with a much smaller buffer size, and outperforms VTM 17.0 (Low-delay B) in terms of PSNR-RGB and MS-SSIM-RGB. The source code of HyTIP is available at https://github.com/NYCU-MAPL/HyTIP.

eess.IV↗

arXiv2025

DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation

This paper presents Deformable Neural Vessel Representations (DeNVeR), an unsupervised approach for vessel segmentation in X-ray angiography videos without annotated ground truth. DeNVeR utilizes optical flow and layer separation techniques, enhancing segmentation accuracy and adaptability through test-time training. Key contributions include a novel layer separation bootstrapping technique, a parallel vessel motion loss, and the integration of Eulerian motion fields for modeling complex vessel dynamics. A significant component of this research is the introduction of the XACV dataset, the first X-ray angiography coronary video dataset with high-quality, manually labeled segmentation ground truth. Extensive evaluations on both XACV and CADICA datasets demonstrate that DeNVeR outperforms current state-of-the-art methods in vessel segmentation accuracy and generalization capability while maintaining temporal coherency.

cs.CV↗

arXiv2024

Microstructural features and hydrogen diffusion in bcc FeCr alloys: a comparison between the Kelvin probe- and nanohardness based- methods

Hydrogen embrittlement can result in a sudden failure in metallic materials, which is particularly harmful in industrially relevant alloys, such as steels. A more comprehensive understanding of hydrogen interactions with microstructural features is critical for preventing hydrogen-induced damage and promoting a hydrogen-based environment-benign economy. We use the Kelvin probe-based potentiometric hydrogen electrode method and thermal desorption spectroscopy to investigate hydrogen interactions with different hydrogen traps in ferritic FeCr alloys with different chromium contents, dislocation densities, and grain sizes. In addition, we confirm the validity of a novel nanohardness-based diffusion coefficient approach by performing in situ nanoindentation testing. Simultaneous acquisition of the dynamic time-resolved mechanical response of FeCr alloys to hydrogen and the hydrogen diffusivities in these alloys is possible during continuous hydrogen supply. Dislocations, grain boundaries and Cr atoms induce reversible hydrogen trapping sites in these ferritic alloys, leading to the reduction of the hydrogen diffusion coefficients and the increase of the absorbed hydrogen.

cond-mat.mtrl-sci↗

arXiv2023

Chemical heterogeneity enhances hydrogen resistance in high-strength steels

When H, the lightest, smallest and most abundant atom in the universe, makes its way into a high-strength alloy (>650 MPa), the material's load-bearing capacity is abruptly lost. This phenomenon, known as H embrittlement, was responsible for the catastrophic and unpredictable failure of large engineering structures in service. The inherent antagonism between high strength requirements and H embrittlement susceptibility strongly hinders the design of lightweight yet reliable structural components needed for carbon-free hydrogen-propelled industries and reduced-emission transportation solutions. Inexpensive and scalable alloying and microstructural solutions that enable both, an intrinsically high resilience to H and high mechanical performance, must be found. Here we introduce a counterintuitive strategy to exploit typically undesired chemical heterogeneity within the material's microstructure that allows the local enhancement of crack resistance and local H trapping, thereby enhancing the resistance against H embrittlement. We deploy this approach to a lightweight, high-strength steel and produce a high-number density Mn-rich zones dispersed within the microstructure. These solute-rich buffer regions allow for local micro-tuning of the phase stability, arresting H-induced microcracks thus interrupting the H-assisted damage evolution chain, regardless of how and when H is introduced and also regardless of the underlying embrittling mechanisms. A superior H embrittlement resistance, increased by a factor of two compared to a reference material with a homogeneous solute distribution within each microstructure constituent, is achieved at no expense of the material's strength and ductility.

cond-mat.mtrl-sci↗

arXiv2022

Hydrogen trapping and embrittlement in high-strength Al-alloys

Ever more stringent regulations on greenhouse gas emissions from transportation motivate efforts to revisit materials used for vehicles. High-strength Al-alloys often used in aircrafts could help reduce the weight of automobiles, but are susceptible to environmental degradation. Hydrogen (H) "embrittlement" is often pointed as the main culprit, however, the mechanisms underpinning failure are elusive: atomic-scale analysis of H inside an alloy remains a challenge, and this prevents deploying alloy design strategies to enhance the materials' durability. Here we successfully performed near-atomic scale analysis of H trapped in second-phase particles and at grain boundaries in a high-strength 7xxx Al-alloy. We used these observations to guide atomistic ab-initio calculations which show that the co-segregation of alloying elements and H favours grain boundary decohesion, while the strong partitioning of H into the second-phases removes solute H from the matrix, hence preventing H-embrittlement. Our insights further advance the mechanistic understanding of H-assisted embrittlement in Al-alloys, emphasizing the role of H-traps in retarding cracking and guiding new alloy design.

cond-mat.mtrl-sci↗