arXiv subjects

Wenyang Zhou

Publications and source records attributed to Wenyang Zhou.

7 recordsLinked to original sources

arXiv2026

PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction

Reconstructing 4D scenes from casually captured monocular video is vital for applications in virtual reality (VR) and embodied AI. Recent advances in 4D reconstruction and novel view synthesis have substantially propelled this capability. However, existing reconstruction methods generally cannot recover regions beyond visible camera limits. Consequently, we introduce a new paradigm that achieves 4D scene synthesis by combining visible-region reconstruction from monocular input with invisible-region generation beyond observable camera boundaries. We present Panoramic Alignment for Strategic Exploitation of Generative Priors (PASTEL). Specifically, PASTEL proposes panoramic scene alignment, a novel representation that reformulates the intractable 3D "invisible region" exploration into a tractable 2D directional trajectory planning. This is achieved by reducing the viewpoint planning from 6-DoF search to a 2D directional search with explicit visibility boundaries. By operating within this panoramic space, our method strategically identifies camera trajectories that maximize exploration beyond observable boundaries while minimizing viewpoint deviation. Experimental results show that PASTEL can not only extrapolate plausible scene content beyond the observable boundaries of input monocular videos, but also substantially boost monocular 4D reconstruction performance. PASTEL outperforms the previous state-of-the-art method by 0.9dB in full-image PSNR on the DyCheck IPhone dataset.

cs.CV↗

arXiv2026

Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis

4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond the observed views. In this paper, we reformulate the task as 4D scene synthesis with unseen regions, which extends beyond traditional interpolation settings. Camera-conditioned video generation enables unseen region synthesis by guiding generation along specified cameras. However, these methods lack explicit 3D priors and are optimized with random camera trajectories. This design leads to severe inconsistencies under large trajectory deviations. To address this limitation, we build a unified training and inference framework with panoramic trajectory guidance. While this design improves cross-view consistency, the panoramic representation alone fails to model dynamic content effectively. Object motion in panoramic space introduces scale and shape distortions. To address this, we propose PanoGaussian, a unified Panoramic-Gaussian representation that distills the panoramic representation into an explicit dynamic Gaussian representation to capture dynamic physical priors of the 4D scene. Experiments demonstrate that PanoGaussian achieves consistent 4D scene synthesis even under large viewpoint variations.

cs.CV↗

arXiv2026

Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening

In this work, we propose a Multigrain-aware Semantic Prototype Scanning paradigm for pan-sharpening, built upon a high-order RWKV architecture and a tri-token prompting mechanism derived from semantic clustering. Specifically, our method contains three key components: 1) Multigrain-aware Semantic Prototype Scanning. Although RWKV offers a efficient linear-complexity alternative to Transformers, its conventional bidirectional raster scanning is still semantic-agnostic and prone to positional bias. To address this issue, we introduce a semantic-driven scanning strategy that leverages locality-sensitive hashing to group semantically related regions and construct multi-grain semantic prototypes, enabling context-aware token reordering and more coherent global interaction. 2) Tri-token Prompt Learning. We design a tri-token prompting mechanism consisting of a global token, cluster-derived prototype tokens, and a learnable register token. The global and prototype tokens provide complementary semantic priors for RWKV modeling, while the register token helps suppress noisy and artifact-prone intermediate representations. 3) Invertible Q-Shift. To counteract spatial details, we apply center difference convolution on the value pathway to inject high-frequency information, and introduce an invertible multi-scale Q-shift operation for efficient and lossless feature transformation without parameter-heavy receptive field expansion. Experimental results demonstrate the superiority of our method.

cs.CV↗

arXiv2026

Fast Tuning the Index Construction Parameters of Proximity Graphs in Vector Databases

k-approximate nearest neighbor search (k-ANNS) in high-dimensional vector spaces is a fundamental problem across many fields. With the advent of vector databases and retrieval-augmented generation, k-ANNS has garnered increasing attention. Among existing methods, proximity graphs (PG) based approaches are the state-of-the-art (SOTA) methods. However, the construction parameters of PGs significantly impact their search performance. Before constructing a PG for a given dataset, it is essential to tune these parameters, which first recommends a set of promising parameters and then estimates the quality of each parameter by building the corresponding PG and then testing its k-ANNS performance. Given that the construction complexity of PGs is superlinear, building and evaluating graph indexes accounts for the primary cost of parameter tuning. Unfortunately, there is currently no method considered and optimized this process.In this paper, we introduce FastPGT, an efficient framework for tuning the PG construction parameters. FastPGT accelerates parameter estimation by building multiple PGs simultaneously, thereby reducing repeated computations. Moreover, we modify the SOTA tuning model to recommend multiple parameters at once, which can be efficiently estimated using our method of building multiple PGs simultaneously. Through extensive experiments on real-world datasets, we demonstrate that FastPGT achieves up to 2.37x speedup over the SOTA method VDTuner, without compromising tuning quality.

cs.DB↗

arXiv2024

EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation

We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. On the one hand, previous works, like motion latent diffusion, conduct diffusion within a latent space for efficiency, but learning such a latent space can be a non-trivial effort. On the other hand, accelerating generation by naively increasing the sampling step size, e.g., DDIM, often leads to quality degradation as it fails to approximate the complex denoising distribution. To address these issues, we propose EMDM, which captures the complex distribution during multiple sampling steps in the diffusion model, allowing for much fewer sampling steps and significant acceleration in generation. This is achieved by a conditional denoising diffusion GAN to capture multimodal data distributions among arbitrary (and potentially larger) step sizes conditioned on control signals, enabling fewer-step motion sampling with high fidelity and diversity. To minimize undesired motion artifacts, geometric losses are imposed during network learning. As a result, EMDM achieves real-time motion generation and significantly improves the efficiency of motion diffusion models compared to existing methods while achieving high-quality motion generation. Our code will be publicly available upon publication.

cs.CV↗

arXiv2024

Specular: Towards Secure, Trust-minimized Optimistic Blockchain Execution

An optimistic rollup (ORU) scales a blockchain's throughput by delegating computation to an untrusted remote chain (L2), refereeing any state claim disagreements between mutually distrusting L2 operators via an interactive dispute resolution protocol. State-of-the-art ORUs employ a monolithic dispute resolution protocol that tightly couples an L1 referee with a specific L2 client binary--oblivious to the system's higher-level semantics. We argue that this approach (1) magnifies monoculture failure risk, by precluding trust-minimized and permissionless participation using operator-chosen client software; (2) leads to an unnecessarily large and difficult-to-audit TCB; and, (3) suffers from a frequently-triggered, yet opaque upgrade process--both further increasing auditing overhead, and broadening the governance attack surface. To address these concerns, we outline a methodology for designing a secure and resilient ORU with a minimal TCB, by facilitating opportunistic 1-of-N-version programming. Due to its unique challenges and opportunities, we ground this work concretely in the context of the Ethereum ecosystem--where ORUs have gained significant traction. Specifically, we design a semantically-aware proof system, natively targeting the EVM and its instruction set. We present an implementation in a new ORU, Specular, that opportunistically leverages Ethereum's existing client diversity with minimal source modification, demonstrating our approach's feasibility.

cs.CR↗

arXiv2023

LC-NeRF: Local Controllable Face Generation in Neural Randiance Field

3D face generation has achieved high visual quality and 3D consistency thanks to the development of neural radiance fields (NeRF). Recently, to generate and edit 3D faces with NeRF representation, some methods are proposed and achieve good results in decoupling geometry and texture. The latent codes of these generative models affect the whole face, and hence modifications to these codes cause the entire face to change. However, users usually edit a local region when editing faces and do not want other regions to be affected. Since changes to the latent code affect global generation results, these methods do not allow for fine-grained control of local facial regions. To improve local controllability in NeRF-based face editing, we propose LC-NeRF, which is composed of a Local Region Generators Module and a Spatial-Aware Fusion Module, allowing for local geometry and texture control of local facial regions. Qualitative and quantitative evaluations show that our method provides better local editing than state-of-the-art face editing methods. Our method also performs well in downstream tasks, such as text-driven facial image editing.

cs.CV↗