44 accepted papers
Dynamic 3D scene reconstruction is essential for immersive media such as VR, MR, and XR, yet remains challenging for long multi-view sequences with large-scale motion. Existing dynamic Gaussian approaches are either Frame-Stream, offering scalability but poor temporal stability, or Clip, achieving l
Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale applications.We present FlashMesh, a fast and high-fidelity mesh generation frame
3D Gaussian Splatting (3DGS) represents scenes through primitives with coupled intrinsic properties: geometric attributes (position, covariance, opacity) and appearance attributes (view-dependent color). Faithful reconstruction requires intrinsic geometry-appearance consistency, where geometry accur
The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agentic T2I methods emerged to alleviate this bottleneck by using multiple models. However, existing agentic T2I methods suf
Reconstructing 3D scenes from multi-view image sequences remains a significant challenge in practical applications. While recent advances in 3D Gaussian Splatting have enabled high-quality rendering, existing methods rely heavily on pixel-level L1 loss, which misaligns with human perception, leading
Perceptual image compression has recently gained increasing attention, as it aims to reconstruct visually realistic images using generative models. Most existing methods adopt patch-based generative adversarial networks (PatchGAN) for one-step image generation, where adversarial training helps the d
Spiking Transformer has sparked growing interest, with the Spiking Self-Attention merging spikes with self-attention to deliver both energy efficiency and competitive performance. However, existing work primarily focuses on 2D visual tasks, and in the domain of 3D point clouds, the disorder and comp…
Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current high-resolution video frame based on temporally previous frames. Most of the existing online VSR methods solely employ one neighboring previous frame to…
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the implicit representation of spatial textures in 3D Gaussian Spla…
Recently proposed 3D Gaussian Splatting (3DGS) has achieved state-of-the-art results in the fields of novel view synthesis, but it heavily relies on pre-computed camera poses. Although recent methods mitigate by leveraging explicit representations achieve novel view synthesis without requiring camer…
The success of 3D Gaussian Splatting (3DGS) in static scenes has inspired numerous attempts to construct Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos. Despite advancements in current techniques, simultaneously achieving photo-realistic view synthesis results, fast on-the-fly…
Recently, 3D Gaussian Splatting (3D-GS) has demonstrated impressive results in novel view synthesis, achieving outstanding rendering quality and speed. However, 3D-GS heavily relies on the quality of the initial point cloud, and its original Adaptive Density Control (ADC) module has difficulty handl…
3D scene understanding is vital for applications in autonomous driving, robotics, and augmented reality. However, scene understanding based on 3D Gaussian Splatting faces three key challenges: (i) an imbalance between appearance and semantics, (ii) inconsistencies in object boundaries, and (iii) dif…
Building Free-Viewpoint Videos in a streaming manner offers the advantage of rapid responsiveness compared to offline training methods, greatly enhancing user experience. However, current streaming approaches face challenges of high per-frame reconstruction time (10s+) and error accumulation, limiti…
Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited to modeling fine-scale motion, greatly restricting their app…
3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and immersive experiences. However, existing online methods face challenge in prohibitive storage requirements primarily due…
3D Gaussian Splatting (3DGS) has recently made breakthrough progress in radiance field reconstruction but struggles with multi-view inconsistency. Modern cameras often apply tailored enhancements to each view when capturing multi-view images. While this improves individual image quality, it inevitab…
Synthesizing novel views from sparse input images is a significant and challenging problem in neural rendering. As an innovative 3D representation, 3D Gaussian Splatting (3DGS) has demonstrated exceptional performance and real-time rendering capabilities. However, rendering novel views from few-shot…
Recently, 3D Gaussian Splatting (3DGS) has achieved state-of-the-art rendering results. However, its efficiency relies on simplifications that disregard the thickness of Gaussian primitives and their overlapping interactions. These simplifications can lead to popping artifacts due to inaccurate sort…
3D Gaussian Splatting (3DGS) has emerged as a premier method for 3D representation due to its real-time rendering and high-quality outputs, underscoring the critical need to protect the privacy of 3D assets. Traditional NeRF steganography methods fail to address the explicit nature of 3DGS since its…
Novel view synthesis has long been a practical but challenging task, although the introduction of numerous methods to solve this problem, even combining advanced representations like 3D Gaussian Splatting, they still struggle to recover high-quality results and often consume too much storage memory…
Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and severe self-occlusions. While recent approaches leverage SMPL estimation and SMPL-conditioned image generative models to h…
Inverse tone mapping (ITM) aims to reconstruct high dynamic range (HDR) radiance from low dynamic range (LDR) content. Although many deep image ITM methods can generate impressive results the field of video ITM is still to be explored. Processing video sequences by image ITM methods may cause tempor…
Learning neural radiance fields (NeRF) without camera poses has been widely studied. However, recent methods lack explicit and effective supervision for pose estimation, resulting in ambiguous optimization of camera pose and NeRF geometry during joint training, particularly in scenarios involving la…
Neural Radiance Field (NeRF) shows a high prospect in the task of novel view synthesis. However, performance degrades drastically under limited input views since NeRF heavily relies on a large number of images to fit the geometry in scenes. Recent efforts focus on introducing extra constraints to im…
Learned video compression has developed rapidly and shown promising rate-distortion performance recently. Existing works have made great progress on removing temporal redundancy between inter-frames, while neglecting spatial redundancy within a frame. In this paper, we propose to explore spatial red…
High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction algorithms recent advancements still struggle with loose or ov…
With the rapid development of 3D movie and light-field displays, there is a growing demand for stereo videos. However, generating high-quality stereo videos from planar videos remains a challenging task. Traditional depth-image-based rendering techniques struggle to effectively handle the problem of…
Despite the substantial progress of novel view synthesis, existing methods, either based on the Neural Radiance Fields (NeRF) or more recently 3D Gaussian Splatting (3DGS), suffer significant degradation when the input becomes sparse. Numerous efforts have been introduced to alleviate this problem,…
Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which may suffer from two limitations: indistinguishable regions and view-dependent effects, e.g., low-textured areas and refl…
Combining the signed distance function (SDF) and differentiable volume rendering has emerged as a powerful paradigm for surface reconstruction from multi-view images without 3D supervision. However, current methods are impeded by requiring long-time per-scene optimizations and cannot generalize to n…
Recent cascade Multi-View Stereo (MVS) methods can efficiently estimate high-resolution depth maps through narrowing hypothesis ranges. However, previous methods ignored the vital geometric information embedded in coarse stages, leading to vulnerable cost matching and sub-optimal reconstruction resu…
The completeness of reconstructed models in low-textured areas in multi-view stereo is still a challenging problem because of the unreliable photometric consistency. Since these areas always exhibit planar properties, many methods explicitly construct planar priors to assist in optimizing depth esti…
Learning-based multi-view stereo (MVS) methods have been widely studied recently. However, current works are limited to using fixed-size convolution kernels, leading to suboptimal features that lack anisotropy in low-textured regions and tend to produce invalid depth blending at the edge of the fore…
In recent years, medical report generation has received increasing research interest with the goal of automatically generating long and coherent descriptive paragraphs that can de-scribe in detail the observations of normal and abnormal regions in the input medical images. Unlike general image capti…
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to…
As depth maps show unique characteristics like piecewise smooth regions bounded by sharp edges at depth discontinuities, new coding tools are required to approximate these signal characteristics. Moreover, the number of bits to signal the residual values for each segment can be further reduced by in…
Self-supervised methods play an increasingly important role in monocular depth estimation due to their great potential and low annotation cost. To close the gap with supervised methods, recent works take advantage of extra constraints, e.g., semantic segmentation. However, these methods will inevita…
Video frame interpolation (VFI) aims at synthesizing new video frames in-between existing frames to generate smoother high frame rate videos. Current methods usually use the fixed pre-trained networks to generate interpolated-frames for different resolutions and scenes. However, the fixed pre-traine…
One of the most challenging problems of novel view synthesis is to predict the scene in complex geometric environments. Existing methods depend on either homography optimization or deep neural networks. In this paper, we provide a framework of view synthesis, which includes grid-based warp, depth re…
Merge prediction is a practical inter-technique in HEVC, which can significantly improve the coding efficiency, especially for homogeneous regions in video sequences. In this paper, a motion aided merge mode (MAMM) is proposed to achieve a better trade-off between the prediction accuracy and bit rat…
Cross-modal retrieval, which aims to solve the problem that the query and the retrieved results are from different modality, becomes more and more essential with the development of the Internet. In this paper, we mainly focus on the exploration of high-level semantic representation of image and text…
Contexts are crucial for action recognition in video. Current methods often mine contexts after extracting hierarchical local features and focus on their high-order encodings. This paper instead explores contexts as early as possible and leverages their evolutions for action recognition. In particul…
Many successful systems for scene recognition transform low-level descriptors into complex representations. This process consists of the two steps: 1) feature coding, which performs a pointwise transformation of the descriptors into a representation adapted to the task, and 2) image pooling, which s…