论文标题
连续对象表示网络：无目标视图监督的新型视图综合
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
论文作者
论文摘要
新型视图合成（NVS）与一个或多个输入图像的摄像机观点转换下的综合视图有关。 NV需要明确的推理，大约是3D对象结构，并且场景中看不见的部分以综合令人信服的结果。结果，当前的方法通常依靠地面真相3D模型或多个目标图像的监督培训。我们提出了连续的对象表示网络（玉米），这是一种条件体系结构，编码输入图像的几何形状和外观，将映射到3D一致的场景表示形式。我们可以通过将模型与神经渲染器相结合，只能使用每个物体的两个源图像训练玉米。玉米的一个关键特征是它不需要地面真相3D模型或目标视图监督。无论如何，玉米在具有挑战性的任务上表现良好，例如新型视图合成和单视3D重建，并实现与使用直接监督的最新方法相当的性能。有关最新信息，数据和代码，请参阅我们的项目页面：https：//nicolaihaeni.github.io/corn/。
Novel View Synthesis (NVS) is concerned with synthesizing views under camera viewpoint transformations from one or multiple input images. NVS requires explicit reasoning about 3D object structure and unseen parts of the scene to synthesize convincing results. As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images. We propose Continuous Object Representation Networks (CORN), a conditional architecture that encodes an input image's geometry and appearance that map to a 3D consistent scene representation. We can train CORN with only two source images per object by combining our model with a neural renderer. A key feature of CORN is that it requires no ground truth 3D models or target view supervision. Regardless, CORN performs well on challenging tasks such as novel view synthesis and single-view 3D reconstruction and achieves performance comparable to state-of-the-art approaches that use direct supervision. For up-to-date information, data, and code, please see our project page: https://nicolaihaeni.github.io/corn/.
