Related papers: Scaling Sequence-to-Sequence Generative Neural Ren…

We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying…

Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes,…

With advancements in deep model architectures, tasks in computer vision can reach optimal convergence provided proper data preprocessing and model parameter initialization. However, training on datasets with low feature-richness for complex…

In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are…

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…

Recently, text-to-3D approaches have achieved high-fidelity 3D content generation using text description. However, the generated objects are stochastic and lack fine-grained control. Sketches provide a cheap approach to introduce such…

Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synthetic data, which have difficulty in inference from real…

We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views using a set of nearby input views. However, the rendering speed…

We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images…

Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream…

Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce…

We present a sketch-based CAD modeling system, where users create objects incrementally by sketching the desired shape edits, which our system automatically translates to CAD operations. Our approach is motivated by the close similarities…

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of…

The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datasets. However, it continues to be hindered by the lack of…

The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These…

Neural rendering methods can achieve near-photorealistic image synthesis of scenes from posed input images. However, when the images are imperfect, e.g., captured in very low-light conditions, state-of-the-art methods fail to reconstruct…

Traditional rendering pipelines rely on complex assets, accurate materials and lighting, and substantial computational resources to produce realistic imagery, yet they still face challenges in scalability and realism for populated dynamic…

Existing text-based 3D generation methods generate attractive results but lack detailed geometry control. Sketches, known for their conciseness and expressiveness, have contributed to intuitive 3D modeling but are confined to producing…