demo.py bug for DL3DV example

[ADSR1042]

command: python demo.py --data_path assets_demo_cli --data_items dl3d140-165f5af8bfe32f70595a1c9393a6e442acf7af019998275144f605b89a306557 --num_inputs 9 --video_save_fps 10

TypeError (note: full exception trace is shown but execution is paused at: _run_module_as_main)
unsupported operand type(s) for -: 'list' and 'int'
File "/workplace/stable-virtual-camera/seva/eval.py", line 692, in chunk_input_and_test
if len(chunk) == T - len(prefix_inds) or not candidate_input_inds:
File "/workplace/stable-virtual-camera/seva/eval.py", line 1411, in run_one_scene
) = chunk_input_and_test(
File "/workplace/stable-virtual-camera/demo.py", line 382, in main
for _ in video_path_generator:
File "/.conda/envs/SVC/lib/python3.10/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/.conda/envs/SVC/lib/python3.10/site-packages/fire/core.py", line 468, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/.conda/envs/SVC/lib/python3.10/site-packages/fire/core.py", line 135, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/workplace/stable-virtual-camera/demo.py", line 414, in
fire.Fire(main)
File "/.conda/envs/SVC/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/.conda/envs/SVC/lib/python3.10/runpy.py", line 196, in _run_module_as_main (Current frame)
return _run_code(code, main_globals, None,
TypeError: unsupported operand type(s) for -: 'list' and 'int'

Although a similar issue has been raised (Issue #54) and errors can be avoided by setting trajectory priors, to my understanding, as mentioned in CLI_USAGE.md, the DL3DV dataset does not include trajectory priors. This may be an issue that needs to be addressed.