Advances in 3D reconstruction using neural rendering have enabled high-quality 3D capture. However, they often fail when the input imagery is corrupted by motion blur, due to fast motion of the camera or the objects in the scene. This work advances neural rendering techniques in such scenarios by using single-photon avalanche diode (SPAD) arrays, an emerging sensing technology capable of sensing images at extremely high speeds. However, the use of SPADs presents its own set of unique challenges in the form of binary images, that are driven by stochastic photon arrivals. To address this, we introduce PhotonSplat, a framework designed to reconstruct 3D scenes directly from SPAD binary images, effectively navigating the noise vs. blur trade-off. Our approach incorporates a novel 3D spatial filtering technique to reduce noise in the renderings. The framework also supports both no-reference using generative priors and reference-based colorization from a single blurry image, enabling downstream applications such as segmentation, object detection and appearance editing tasks. Additionally, we extend our method to incorporate dynamic scene representations, making it suitable for scenes with moving objects. We further contribute PhotonScenes, a real-world multi-view dataset captured with the SPAD sensors. Code, data and video results are available at vinayak-vg.github.io/PhotonSplat/.

In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest in 3D scene representations such as neural radiance fields from multi-view images. However, the availability of 3D or multiview data is still substantially limited compared to 2D image datasets, making extending 2D vision models to 3D data highly desirable but also very challenging. Indeed, extending a single 2D vision operator like scene editing to 3D typically requires a highly creative method specialized to that task and often requires per-scene optimization. In this paper, we ask the question of whether any 2D vision model can be lifted to make 3D consistent predictions. We answer this question in the affirmative; our new Lift3D method trains to predict unseen views onfeature spaces generated by afew visual models (i.e. DINO and CLIP), but then generalizes to novel vision operators and tasks, such as style transfer, super-resolution, open vocabulary segmentation and image colorization; for some of these tasks, there is no comparable previous 3D method. In many cases, we even outperform state-of-the-art methods specialized for the task in question. Moreover, Lift3D is a zero-shot method, in the sense that it requires no task-specific training, nor scene-specific optimization.

Large Language Models (LLMs) may offer transformative opportunities for text input, especially for physically demanding modalities like handwriting. We studied a form of abbreviated handwriting by designing, developing, and evaluating a prototype, named SkipWriter, that converts handwritten strokes of a variable-length prefix-based abbreviation (e.g., "ho a y" as handwritten strokes) into the intended full phrase (e.g., "how are you" in the digital format) based on the preceding context. SkipWriter consists of an in-production handwriting recognizer and an LLM fine-tuned on this task. With flexible pen input, SkipWriter allows the user to add and revise prefix strokes when predictions do not match the user’s intent. An user evaluation demonstrated a 60% reduction in motor movements with an average speed of 25.78 WPM. We also showed that this reduction is close to the ceiling of our model in an offline simulation.

Cross-scene generalizable NeRF models, which can directly synthesize novel views of unseen scenes, have become a new spotlight of the NeRF field. Several existing attempts rely on increasingly end-to-end "neuralized" architectures, i.e., replacing scene representation and/or rendering modules with performant neural networks such as transformers, and turning novel view synthesis into a feed-forward inference pipeline. While those feedforward "neuralized" architectures still do not fit diverse scenes well out of the box, we propose to bridge them with the powerful Mixture-of-Experts (MoE) idea from large language models (LLMs), which has demonstrated superior generalization ability by balancing between larger overall model capacity and flexible per-instance specialization. Starting from a recent generalizable NeRF architecture called GNT [52], we first demonstrate that MoE can be neatly plugged in to enhance the model. We further customize a shared permanent expert and a geometry-aware consistency loss to enforce cross-scene consistency and spatial smoothness respectively, which are essential for generalizable view synthesis. Our proposed model, dubbed GNT with Mixture-of-View-Experts (GNT-MOVE), has experimentally shown state-of-the-art results when transferring to unseen scenes, indicating remarkably better cross-scene generalization in both zero-shot and few-shot settings. Our codes are available at https://github.com/VITA-Group/GNT-MOVE.

Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

Improving the performance of deep networks in data-limited regimes has warranted much attention. In this work, we empirically show that “winning tickets” (small sub-networks) obtained via magnitude pruning based on the lottery ticket hypothesis, apart from being sparse are also effective recognizers in data-limited regimes. Based on extensive experiments, we find that in low data regimes (datasets of 50-100 examples per class), sparse winning tickets substantially outperform the original dense networks. This approach, when combined with augmentations or fine-tuning from a self-supervised backbone network, shows further improvements in performance by as much as 16% (absolute) on low-sample datasets and long-tailed classification. Further, sparse winning tickets are more robust to synthetic noise and distribution shifts compared to their dense counterparts. Our analysis of winning tickets on small datasets indicates that, though sparse, the networks retain density in the initial layers and their representations are more generalizable. Code is available at https://github.com/VITA-Group/DataEfficientLTH.

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input distribution and cannot learn long-range dependences. Recent works have shown that adding attention in conjunction with these methods improves performance. This raises a question: can attention layers completely replace convolutions? This letter proposes a fully attentional model—Point Transformer (PT) for deriving a rich point cloud representation. The model’s shape classification and retrieval performance are evaluated on a large-scale urban data set—RoofN3D and a standard benchmark data set ModelNet40. Extensive experiments are conducted to test the model’s robustness to unseen point corruptions for analyzing its effectiveness on real data sets. The proposed method outperforms other state-of-the-art models in the RoofN3D data set, gives competitive results in the ModelNet40 benchmark, and shows high robustness to various unseen point corruptions. Furthermore, the model is highly memory and space-efficient when compared to other methods.