Related papers: Sculpt4D: Generating 4D Shapes via Sparse-Attentio…
We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing, notably the inefficiencies of existing 4D representations and the…
Time series generation focuses on modeling the underlying data distribution and resampling to produce authentic time series data. Key components, such as trend and seasonality, drive temporal fluctuations, yet many existing approaches fail…
Entrusted with the goal of pixel-level object classification, the semantic segmentation networks entail the laborious preparation of pixel-level annotation masks. To obtain pixel-level annotation masks for a given class without human…
Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…
The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…
We propose a novel point cloud U-Net diffusion architecture for 3D generative modeling capable of generating high-quality and diverse 3D shapes while maintaining fast generation times. Our network employs a dual-branch architecture,…
Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of…
We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using neural field…
We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph…
Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…
The Gaussian diffusion model, initially designed for image generation, has recently been adapted for 3D point cloud generation. However, these adaptations have not fully considered the intrinsic geometric characteristics of 3D shapes,…
Modeling dynamic scenes through 4D Gaussians offers high visual fidelity and fast rendering speeds, but comes with significant storage overhead. Recent approaches mitigate this cost by aggressively reducing the number of Gaussians. However,…
Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…
Dynamic 4D Gaussian Splatting (4DGS) effectively extends the high-speed rendering capabilities of 3D Gaussian Splatting (3DGS) to represent volumetric videos. However, the large number of Gaussians, substantial temporal redundancies, and…
Generating whole-brain 4D fMRI sequences conditioned on cognitive tasks remains challenging due to the high-dimensional, heterogeneous BOLD dynamics across subjects/acquisitions and the lack of neuroscience-grounded validation. We introduce…
Constructing high-resolution 3D geological models from sparse 1D borehole and 2D surface data is a highly ill-posed inverse problem. Traditional heuristic and implicit modeling methods fundamentally fail to capture non-linear topological…
Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further…
One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising results, have relied on either estimating dense attention to…
We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the ambiguity of possible reconstructions, making generative…
Diffusion based approaches to long form text generation suffer from prohibitive computational cost and memory overhead as sequence length increases. We introduce SA-DiffuSeq, a diffusion framework that integrates sparse attention to…