相关论文: Prompt2NeRF-PIL: Fast NeRF Generation via Pretrain…

2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view NeRF synthesis…

We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method achieves sampling by "pulling back" the dynamics of the…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Recent advancements in generative models have enabled the creation of dynamic 4D content - 3D objects in motion - based on text prompts, which holds potential for applications in virtual worlds, media, and gaming. Existing methods provide…

We propose the NeRF-LEBM, a likelihood-based top-down 3D-aware 2D image generative model that incorporates 3D representation via Neural Radiance Fields (NeRF) and 2D imaging process via differentiable volume rendering. The model represents…

We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step diffusion and flow-matching image generation models. Unlike existing approaches such as classifier-free guidance (CFG),…

Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and suffer from…

Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on billions of image-text pairs. Adapting this approach to 3D synthesis would require large-scale datasets of labeled 3D data and efficient…

Neural Radiance Fields (NeRF) have demonstrated remarkable performance in novel view synthesis. However, there is much improvement room on restoring 3D scenes based on NeRF from corrupted images, which are common in natural scene captures…

Procedural Content Generation (PCG) algorithms enable the automatic generation of complex and diverse artifacts. However, they don't provide high-level control over the generated content and typically require domain expertise. In contrast,…

The design of high-performance optical systems remains a specialized domain gated by the limited availability of expert engineers, creating a bottleneck that stalls innovation despite the growing demand for imaging hardware. While deep…

We present Dynamic Neural Portraits, a novel approach to the problem of full-head reenactment. Our method generates photo-realistic video portraits by explicitly controlling head pose, facial expressions and eye gaze. Our proposed…

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enhancing output…

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve…

This paper presents a methodology to learn surrogate models of steady state fluid dynamics simulations on meshed domains, based on Implicit Neural Representations (INRs). The proposed models can be applied directly to unstructured domains…

Neural Radiance Field (NeRF) has exhibited outstanding three-dimensional (3D) reconstruction quality via the novel view synthesis from multi-view images and paired calibrated camera parameters. However, previous NeRF-based systems have been…

Animating high-fidelity video portrait with speech audio is crucial for virtual reality and digital entertainment. While most previous studies rely on accurate explicit structural information, recent works explore the implicit scene…

Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time…

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to…

Prompt-driven image analysis converts a single natural-language instruction into multiple steps: locate, segment, edit, and describe. We present a practical case study of a unified pipeline that combines open-vocabulary detection,…